UrbanAgent: A Tool-Augmented Agent for Cross-System Urban Tasks paper · Jiayu Cao et al.
2026-08-04 2026-10-24 Getting the Parameters Right: A Difficulty-Graded Benchmark and Probe-Guided Training for LLM Tool Calls paper · Guoyao Yu et al.
2026-08-04 2026-10-24 Route-Align-Verify for Functional Correctness in Code Generation paper · Erxue Zhou et al.
2026-08-04 2026-10-24 TimeRLM: Recursive Language Models Enable Precise Anomaly Localization in Long-Context Time-Series paper · Nicolas Zumarraga et al.
2026-08-04 2026-10-24 UHP Detection: LVLMs have their Unique Hallucination Pattern in the Consistency Space paper · Amir Mohammad Ezzati et al.
2026-08-04 2026-10-24 SocietyBench: Forecasting Counterfactual Social-World Evolution paper · Zhenran Wang et al.
2026-08-04 2026-10-24 HyPASE: Hyperbolic Geometry for Parameter-Efficient Speech Emotion Fine-Tuning Framework for Large Audio-Language Models paper · Tian Jin et al.
2026-08-05 2026-10-24 no claims yet RepoProbe: Benchmarking Architecture-Aware Repository Comprehension with Checklists paper · Yuexi Yang et al.
2026-08-05 2026-10-24 no claims yet When Do Corrective Features Help? An Agent for Corrective Feature Discovery on Black-Box Forecasters paper · Fangxin Wang et al.
2026-08-05 2026-10-24 TruthLens: Object Hallucination Detection via Self-Evaluating Truthfulness Scores in LVLMs paper · Yanqi Wu et al.
2026-08-06 2026-10-24 no claims yet ChronoVision: Temporal Reasoning via Latent State Reconstruction paper · Yifan Shen et al.
2026-08-06 2026-10-24 no claims yet StreamArena: Toward Continuous, Interactive, and Long-Horizon Agentic Streaming Video Understanding paper · Xichen Zhang et al.
2026-08-06 2026-10-24 SkillMemo: Expert-guided Skill Memory Framework for Compositional Embodied Manipulation paper · Changyuan Wang et al.
2026-08-06 2026-10-24 Capek 0.5: An Execution-Centric Vision-Language Model for Embodied Intelligence paper · Ying Chen et al.
2026-08-07 2026-10-24 Multi-Agent Forensic Reasoning for Generalizable Deepfake Video Detection paper · Xuechao Zou et al.
2026-08-07 2026-10-24 Agent Memory Distillation: Empowering Small LLM Agents with Hierarchical Teacher Memory paper · Taeil Kim et al.
2026-08-07 2026-10-24 Same Attention, Different Truths: Put Logit-Lens over Visual Attention to Detect and Mitigate LVLM Object Hallucination paper · Zichuan Wang et al.
2026-08-07 2026-10-24 Contextual Value Alignment via Multilayer Combinatorial Fusion paper · Yuanhong Wu et al.
2026-08-07 2026-10-24 no claims yet Counterfactual Benchmarking and Training for Factuality Consistency and Order-Robust Grounded Reasoning in LLMs over Heterogeneous Knowledge paper · Shibo Chu et al.
2026-08-08 2026-10-24 no claims yet Wiener Representation Filtering for VLM Hallucination Suppression paper · Ameen Ali et al.
2026-08-08 2026-10-24 VoxZip: Semantic-Anchored Temporal KV Cache Compression for Long-Context Audio Inference paper · Wenxu Jia et al.
2026-08-09 2026-10-24 DistillCache: KL-Guided Adaptive KV-Cache Eviction for Memory-Efficient LLM Inference paper · Asaad Althoubi
2026-08-09 2026-10-24 Pseudo2CodeQA: A Benchmark for LLM-Based Structured Algorithmic Reasoning in Code Generation paper · Shadikur Rahman et al.
2026-08-10 2026-10-24 no claims yet Beyond Global Editing: Per-Instance Disentangled Subspaces for Training-Free Hallucination Mitigation in LVLMs paper · Ali Cheraghian et al.
2026-08-10 2026-10-24 REATS: LLM Reasoning-based Ensemble Learning for Adaptive Time Series Forecasting paper · Xu Zhang et al.
2026-08-10 2026-10-24 One Recipe, Many Harnesses: What Self-Evolution Encodes Across Languages and Models paper · Siqi Yang et al.
2026-08-10 2026-10-24 no claims yet UniProbe: A Learnable Token-Level Hallucination Detector for Large VLMs using Multi-Structural Internal Representations paper
2026-08-11 2026-10-24 GraphAlignCoder: Aligning Program and Proof Graphs for Code Generation paper
2026-08-11 2026-10-24 Test-Time Hallucination Control in Large Vision-Language Models paper · Mehran Tamjidi et al.
2026-08-11 2026-10-24 When the API Speaks the Wrong Language: Revisiting Post-Training for Multilingual Tool Use paper
2026-08-12 2026-10-24 Advancing MLLM-based UAV Image Understanding and Reasoning: A Benchmark and a Training-Free Multi-Agent System paper · Haoyu Zhang et al.
2026-08-12 2026-10-24 no claims yet VAKRA: Evaluating Multi-Hop Reasoning Across APIs and Retrieval Under Tool-Use Policies paper
2026-08-12 2026-10-24 Large Language Models Can Follow Instructions, But Not Many at Once: Phase Transitions in Compositional Constraint Satisfaction paper
2026-08-12 2026-10-24 Do LLMs Beat Nash? Testing Decentralized Coordination in Self-Play Multi-Agent Games paper
2026-08-12 2026-10-24 LLMs Are Not Good Strategists, Yet Memory-Enhanced Agency Boosts Reasoning paper
2026-08-12 2026-10-24 Discovering Efficient and Explainable Communication Topologies for LLM-based Multi-Agent Systems via Causal Inference paper · Junzhi Li et al.
2026-08-13 2026-10-24 EgoMonth: A Month-Level Egocentric Video Benchmark for Long-Term Spatiotemporal Memory paper
2026-08-13 2026-10-24 Numeracy in Large Language Models: Fundamental Limitations and Paths to Improvement paper · Aoxin Ni
2026-08-13 2026-10-24 Refine After Generation: Toward Correct and Concise Patches in LLM-based Program Repair paper · Wenqiang Luo et al.
2026-08-13 2026-10-24 MLLM-Routed Heterogeneous Ensembles for Robust Cross-Dataset Image Classification paper · Daniel Perkins et al.
2026-08-13 2026-10-24 MedClaw: Heuristic Agent Harness for Long-Horizon Surgical Video Reasoning paper
2026-08-14 2026-10-24 Semantic Uncertainty-Guided Orchestration in Hierarchical Multi-Agent Systems paper
2026-08-11 2026-10-24 From Sequence to Structure: Relational Uncertainty Propagation for LLM Agents paper
2026-08-17 2026-10-24 Hierarchical Skill Retrieval for Data-Efficient Adaptation of Vision-Language-Action Models paper
2026-08-25 2026-10-24 Agentopia on a Consumer GPU: A Reduced-Scale Long-Horizon Port with an 8B Model paper
2026-08-25 2026-10-24 VideoHarness-RSI: Recursive Harness Self-Improvement for Long-Video Understanding with Frozen Vision-Language Models paper
2026-08-25 2026-10-24 Do Recipes Have Personas? Characterizing and Generating Creator Style in Attributed Procedural Graphs paper
2026-08-25 2026-10-24 EviDx: Evidence-Aware Active Diagnosis with Scaffolded LLM Agents paper
2026-08-25 2026-10-24 A Control-Theoretic Approach for Resource-Aware Consensus in Multi-Agent AI paper
2026-08-25 2026-10-24 GRIP: Granular Reward-Guided Parameter Interpolation for Efficient Reasoning paper
2026-08-26 2026-10-24 From General Agents to RCA Experts: A Self-Evolving Harness for Root Cause Analysis paper
2026-08-26 2026-10-24 Localize-Then-Decide Guarantees for LLM Judgments paper
2026-08-26 2026-10-24 Anchoring Bias in LLM-as-a-Judge Systems: Prior Scores Compromise Evaluation Independence paper
2026-08-26 2026-10-24 Repair or Resample? Rethinking Failure Debugging in LLM Multi-Agent Systems paper
2026-08-26 2026-10-24 ProgRouter: Online Progress-Guided Orchestration for Multi-Agent LLM Workflows under Quality-Cost Tradeoffs paper
2026-08-26 2026-10-24 A Self-Evolving Multi-Agent Framework Defense against LLM Jailbreak Attacks paper
2026-08-26 2026-10-24 SwarmWorld: Stigmergic technological evolution in societies of language-model agents paper
2026-08-26 2026-10-24 SKILL.state: Scalable Long-Horizon Agent Skills paper
2026-08-26 2026-10-24 Neuro-symbolic PRM: Enhancing Scientific Reasoning via Structured Traces and Symbolic Verification paper
2026-08-26 2026-10-24 Benchmarking Clinical Decision Pathway Adherence in Large Language Models paper
2026-08-27 2026-10-24 Not Just Reason, Not Just Scan: Reinforcement Learning for Proactive Scientific Error Verification over Academic Paper paper
2026-08-27 2026-10-24 Evaluating Confidence-Gated Retrieval with Matched Trajectory Replay paper
2026-08-27 2026-10-24 4DSynth: Controllable Procedural World Synthesis for Dynamic Embodied Simulation paper
2026-08-27 2026-10-24 Direct or Mediated? Task-Dependent Audio Information Routing in Large Audio Language Models paper
2026-08-27 2026-10-24 Video-OPSD: Exploiting Privileged Visual Evidence for On-Policy Self-Distillation in Video Large Language Models paper
2026-08-27 2026-10-24 Verify Smarter, Evolve Further: Efficient Harness Evolution through Behavior-Aware Verification paper
2026-08-27 2026-10-24 NormasTCU --- A Brazilian Portuguese IR Dataset and an Evaluation of LLM-as-a-Judge for Relevance Assessment paper
2026-08-27 2026-10-24 Load-Bearing Context: The Question Damage Score for Evaluating Context Reliance in Linguistic Reasoning paper
2026-08-27 2026-10-24 Temporal Tree of Thought: Reasoning-Guided Visual Cue Search for Long-Video Understanding paper
2026-08-28 2026-10-24 When Evidence Shapes Collaboration: Knowledge-Conditioned Topology Generation for Multi-Agent Systems paper
2026-08-28 2026-10-24 Twin Worlds: Equivariance-Based Abstention for Evidence-Grounded Reasoning paper
2026-08-28 2026-10-24 CoCoBench: A Cooperative Coordination Benchmark for Embodied Multi-Agent Task Planning paper
2026-08-28 2026-10-24 When Linguistic and Internal Confidence Diverge in Large Language Models paper
2026-08-28 2026-10-24 Recognition-Refusal Misalignment in LLMs: Why Models Answer Structurally Unanswerable Questions paper
2026-08-29 2026-10-24 HalluPrism: When Multimodal Uncertainty Should Diagnose, Not Decide paper
2026-08-29 2026-10-24 Bridging Semantics and Physics with Constrained LLMs for Safe and Trustworthy Robotic Manipulation paper
2026-08-29 2026-10-24 Evaluating LLMs on Conversational Text-to-SQL under Chain Ambiguity and Intent Drift paper
2026-08-30 2026-10-24 Harness-RL: Black-Box Reinforcement Learning with Action-Args Decoupling for Central-Agent Multi-Agent Harnesses paper
2026-08-30 2026-10-24 Evaluating the Capabilities of LLMs for Persuasive Dialogue paper
2026-08-30 2026-10-24 RIDGE: Region-Informed Derivative-Guided Evidence Selection for Long Video Understanding paper
2026-08-30 2026-10-24 DataFoundry: Evolving Data Preparators via Recursive Self-Improvement paper
2026-08-30 2026-10-24 Error Detection for PET/CT Radiology Reports: Domain-Specific vs Large Language Models paper
2026-08-30 2026-10-24 Dense Clinical Contrasts Enhance Medical Knowledge Updating in Large Language Models paper
2026-08-31 2026-10-24 CM2: Multimodal Cultural Reasoning via an Integrated Multi-Agent Framework paper
2026-08-31 2026-10-24 E-Commerce Bench: Evaluating LLM Agents on Long-Horizon Autonomous Business Operation paper
2026-08-31 2026-10-24 Evidence, Logic, and Compliance: Multi-Agent Structured Graph Reasoning with Expert Arbitration for Medical Referral paper
2026-08-31 2026-10-24 Good Memory Has ECC: Evaluating the Memory of Vision-Language Models Beyond Accuracy paper
2026-08-31 2026-10-24 Uncovering and Mitigating Aggregation-Induced Reward Hacking in Multi-Reward Reinforcement Learning paper
2026-08-31 2026-10-24 WorldBench: Culturally Grounded Benchmark for Multilingual Agents paper
2026-09-01 2026-10-24 When Guardrails Look Effective: Construct Validity Failures in LLM Agent Commerce Evaluation paper
2026-09-01 2026-10-24 TAG-Bench: Benchmarking Temporal Audio Grounding in Large Audio Language Models paper
2026-09-01 2026-10-24 How Fast Do Agents Rot? An Empirical Study of Long-Horizon Degradation in LLM Agents for Production Decision-Making paper
2026-08-31 2026-10-24 Agents That Model Agents: Five Principles Toward a Theory of Mind for 6G Networks paper
2026-09-01 2026-10-24 Beyond Human-Likeness: Mapping the Scientific Critique Profiles of LLMs and Human Reviewers paper
2026-09-01 2026-10-24 Engineered Persuasion: Evaluating Personalized Pretexts in LLM-Generated Spear Phishing paper
2026-09-03 2026-10-24 A Structured Debate-Mixture-of-Agents Framework for Complex Clinical Diagnostic Decision Support paper
2026-09-04 2026-10-24 SureRoute: Toward a Hallucination-Free Self-Improving Platform for Retrosynthesis paper · Jieli Zhou et al.
2026-08-04 2026-10-24 Solving versus Verifying: Catching Contradictions in Tax Reasoning Systems paper
2026-09-05 2026-10-24 Uncertainty Quantification for LLM Agents: A Taxonomy, an Evaluation Protocol, and an Empirical Study paper
2026-09-07 2026-10-24 Do Large Language Models Know What They Don't Know II? A Fully Behavioral, Non-Cognitive Measure of Epistemic Honesty paper
2026-09-07 2026-10-24 COAL-SQL: Coverage-Guided Augmentation and Failure-Driven Learning for Text-to-SQL Post-Training paper · Qifeng Cai et al.
2026-08-04 2026-10-24 Gradient Routing Localizes and Removes Unintended Behaviors in RL paper · Jake Ward et al.
2026-10-12 2026-10-20 Position: Embracing Negative Results in Machine Learning paper · Florian Karl et al.
2024-06-06 2026-10-19 ReasoningBank: Scaling Agent Self-Evolving with Reasoning Memory paper · Siru Ouyang et al.
2025-09-29 2026-10-19 LLMs Have Made Failure Worth Publishing paper · Sungmin Lee
2026-04-04 2026-10-19 Negative results are disappearing from most disciplines and countries paper · Daniele Fanelli
2011-09-11 2026-10-19 An Excess of Positive Results: Comparing the Standard Psychology Literature With Registered Reports paper · Anne M. Scheel et al.
2021-04-01 2026-10-19 Thinking Inertia: LLMs Keep Thinking When Told Not To paper · Dianqiao Lei et al.
2026-10-08 2026-10-18 Actionable Hallucination Detection: Translating Latent Uncertainty into Agentic Critique paper · Sanidhya Vijayvargiya et al.
2026-08-11 2026-10-17 Co-RL: Unsupervised Reasoning Emerges from Diverse Cohort in Multi-agent RL paper · Yunhao Yang et al.
2026-08-18 2026-10-17 Counterfactual Anatomy-guided Spatial-Temporal Decoding for Annotation-Free Hallucination Mitigation in Medical VLMs paper · Yifan Lu et al.
2026-08-18 2026-10-17 FM-Bench: A Benchmark for Long-Horizon Management with Competing Agents paper · Tianyou Wang et al.
2026-08-19 2026-10-17 MR-IQA-2: Faithful Image Quality Reflection via Fine-Grained Credit Assignment paper · Yuan li et al.
2026-08-19 2026-10-17 Training-Free Inference-Time Self-Reflection and Cost-Bounded Early Stopping for Large Language Models paper · Wei Yu et al.
2026-08-19 2026-10-17 ReWEIGH the Evidence: Calibrating Token-Level Ordinal Visual Evidence to Mitigate Hallucinations in Large Vision-Language Models paper · Jihae Jeong et al.
2026-08-19 2026-10-17 Repo0: Design-Driven Zero-to-All Code Generation paper · Silin Chen et al.
2026-08-20 2026-10-17 MidTool: Mid-training Data Synthesis for Agentic Tool Use paper · Fengqing Jiang et al.
2026-08-20 2026-10-17 MGAL: A Multilingual Granularity-Aware Long-Context Benchmark paper · Chunhan Li et al.
2026-08-21 2026-10-17 Belief Without Behavior: Measuring the Translation of Theory of Mind into Coordinated Social Action in Vision-Language Models paper · Tonglin Yan et al.
2026-08-21 2026-10-17 COMET: Contrastive Motion-Enhanced Temporal Reasoning for Video Multimodal Large Language Models paper · Chenghua Zhu et al.
2026-08-21 2026-10-17 Measuring Activation Control in Large Language Models paper · Marek Mateusz Kowalski et al.
2026-08-21 2026-10-17 Semantic Reasoning Denoising: Correcting Language Model Reasoning with Semantic Operators paper · Yujiao Yang
2026-08-22 2026-10-17 Claim-Level Confidence Calibration for Reliable Decision Making with Large Language Models paper · Toghrul Abbasli et al.
2026-08-23 2026-10-17 Coalition-Aware Skill Reliability for Self-Evolving Agents paper · Qiyan Zhao et al.
2026-08-23 2026-10-17 Frontiers in FinTech: Multimodal Foundation Models for Financial Reporting and Decision Science paper · Yulu Huang et al.
2026-08-24 2026-10-17 LLM-based Agents for Forecasting and Prediction: Methods, Training, Evaluation, and Applications paper · Xiaogang Xu et al.
2026-08-24 2026-10-17 Credal Large Language Models for Semantic Commitment under Uncertainty paper · Shireen Kudukkil Manchingal et al.
2026-08-24 2026-10-17 FPGAgent: An LLM-Assisted Framework for Autonomous HLS Code Generation and Verification in FPGA Environments paper · Tianyu Wang et al.
2026-08-23 2026-10-17 ToolRobustBench: Stage-Wise Perturbation Evaluation and Failure Diagnosis for Tool-Calling Agents paper · Zheng Yishan et al.
2026-08-23 2026-10-17 Preference Data Selection for Mitigating the Alignment Tax in Large Language Models paper
2026-08-25 2026-10-17 MoTE: Mixture of Task Experts for Multi-Task Video Understanding paper · Muhammad Asad Ali et al.
2026-08-25 2026-10-17 Belief Cascades Drive Persuasion in LLM Agent Networks paper
2026-08-25 2026-10-17 Beam Search, Self-Consistency, and the Limits of Inference-Time Scaling for Grammar-Constrained Text-to-SQL in Small Language Models paper
2026-08-26 2026-10-17 AesCanvas: A Large-Scale Dataset and Benchmark for Aesthetic Critique and Contextual Suitability paper
2026-08-27 2026-10-17 BekchiAI: Measuring, Observing, and Controlling LLM Agents in One Click paper
2026-08-27 2026-10-17 STEP: State-Aware Task Estimation and Planning with Multi-Modal LLMs for Human-Robot Collaboration paper
2026-08-27 2026-10-17 One Model, Many Minds: Unlocking Multi-Agent Synergy in a Single Agent via Mixture of Roles paper · Zhichen Zeng et al.
2026-08-27 2026-10-17 CritICL: Inference-Time Weak-to-Strong Generalization from Small Language Model Failure Modes paper · Yufan Wu et al.
2026-08-27 2026-10-17 Finding Where the Buck Stops: An Automated Failure Attribution-Based Reflection Framework for Multi-Agent Collaboration paper · Xiaoqing Wang et al.
2026-08-28 2026-10-17 Learning Simple Test-Time Environments for LLM Web Agents paper
2026-08-29 2026-10-17 BIRD-History: A Benchmark for History-Driven Text-to-SQL with Fine-Grained Knowledge Annotations paper
2026-08-29 2026-10-17 A Cognitive Architecture for Shared Autonomy in AUV Operations paper
2026-08-29 2026-10-17 AGM: Achievement-Grounded Memory for Closed-Loop Agents with Frozen VLA Policies paper
2026-08-30 2026-10-17 AgenticRag-R1: Agentic Reinforcement Learning with Stack Memory for Multi-Step Reasoning, Retrieval and Memorizing paper · Xinke Jiang et al.
2026-08-30 2026-10-17 FRAMEWORKERS: A Dynamic Multi-Agent Framework for AI-Generated Video Production paper
2026-08-30 2026-10-17 Beyond Fluency: A Rubric-Based Benchmark for Evaluating Saudi Dialect and Cultural Competence in Large Language Models paper · Ghassan Al-Sumaidaee et al.
2026-08-30 2026-10-17 CPR for LLMs: Critical-Point Routing against Catastrophic Forgetting in Domain Adaptation paper · Kwangmin Ki et al.
2026-08-31 2026-10-17 More Capable, Less Faithful: A Multilingual Analysis of Mathematical (Un)Solvability Detection in LLMs paper · Maria-Eleni Zoumpoulidi et al.
2026-08-31 2026-10-17 SwarmBench: Can Large Language Models Act as Agent Swarm Orchestrators? paper
2026-08-31 2026-10-17 HiRS-Agent: A Hierarchical Multi-Agent System for Reliable Long-Horizon Remote Sensing Task Solving paper · Boyang Mu et al.
2026-08-31 2026-10-17 LCoT-GV: Graph Attention Networks for Verifying Long Reasoning Chains in Large Language Models paper
2026-08-31 2026-10-17 HSRM: Hidden-State Reward Models for Test-Time Verification paper
2026-08-31 2026-10-17 LightNav-0: Eliciting VLM Spatial Intelligence for Generalist Embodied Navigation paper · Shaoan Wang et al.
2026-08-31 2026-10-17 S3Gym: Can LLMs Turn Self-Testing and Self-Judging into Self-Improvement? paper
2026-08-31 2026-10-17 Learning What to Retain: Gated-Memory Routing for Efficient Collaboration in Multi-Agent LLM Systems paper
2026-08-31 2026-10-17 VoiceLongMemEval: Do Assistants Remember How You Sounded? paper
2026-09-01 2026-10-17 Heard but Not Heeded: Paralinguistic Information Encoding and Loss in Audio-Language Models paper · Bhuvan Koduru et al.
2026-09-01 2026-10-17 Replacing Training with Memory: Listwise Selection for Text-to-SQL paper · Yeonseok Jeong et al.
2026-09-01 2026-10-17 Towards Generalizable Visually Grounded Exploration of Household Devices paper · Linhao Zheng et al.
2026-09-01 2026-10-17 CHARM: Character Hallucination for Multicultural Role Play Benchmark paper
2026-09-01 2026-10-17 Evaluating Multimodal LLMs as Generalist Vision-Language-Action Agents for Drone Control: Commanding, Approaching, Tracking and Searching paper · Jaewoo Park et al.
2026-09-01 2026-10-17 CordisBench: Can Language Models Reason About Component Lifecycles in Dynamic Agent Harnesses? paper
2026-09-01 2026-10-17 PRO-Step: Step-level Process Reward Optimization for Retrieval-Augmented Generation paper
2026-08-31 2026-10-17 CUSP: Decomposable Collective Uncertainty for Multi-Agent Multimodal Reasoning paper
2026-09-04 2026-10-17 UniRRM: Unified Reasoning Reward Models Across Languages and Evaluation Paradigms paper
2026-09-05 2026-10-17 Neuron-Guided Fine-Tuning: Unlocking Efficient Alignment Mechanisms for Large Language Models paper
2026-09-05 2026-10-17 Rethinking the Evaluation of Efficiency Methods for Multi-Agent Systems paper
2026-09-05 2026-10-17 Stable-MM-R1: Anchoring Multimodal Reasoning Dynamics via Entropy-Guided Stratification paper
2026-09-07 2026-10-17 Long-Horizon Language Model Reinforcement Learning via Progressive Point Matching paper
2026-09-07 2026-10-17 Staying on the Attack Path: Structured State for Long-Horizon Automated Penetration Testing paper
2026-09-07 2026-10-17 Environments as Scaffold: Enriching Feedback to Bootstrap Self-Evolving Agents in Long-Horizon Tasks paper
2026-09-08 2026-10-17 StochBench: A Domain-Specific Benchmark for Stochastic Processes in Lean paper
2026-09-08 2026-10-17 Auditable Emergency Triage for Maternal and Newborn Care in India paper
2026-09-08 2026-10-17 Multi-Agent Agentic Graph Learning via Structural Signatures paper
2026-09-09 2026-10-17 Grounded Evaluation and Repair for NL-to-PDDL Problem Generation paper
2026-09-09 2026-10-17 Strangers to Themselves: What Language Models Say About Themselves Is Generic paper
2026-09-09 2026-10-17 Belief-State Engine: Augmenting LLMs for Principled Planning Under Partial Observability paper
2026-09-09 2026-10-17 RAP: Research Attention Prediction Reveals Target-Conditioned Evidence Acquisition Biases paper
2026-09-09 2026-10-17 $Φ$-Bench: Can Large Language Models Engineer the Infrastructure That Powers Them? paper
2026-09-09 2026-10-17 Translating the Translator: Decomposing the Cost of English-Forced Inter-Agent Communication paper
2026-09-14 2026-10-17 The Universe of Universes: Benefit Yield Functions, Implosion Thresholds, and Infrastructure-Aware Optimization in Multi-LLM Systems paper
2026-09-14 2026-10-17 HypoEvolve: Genetic Algorithms Enable Multi-Agent LLMs to Discover Scientific Hypotheses paper
2026-09-14 2026-10-17 BLINDSPOT: A Benchmark for Safety and Refusal Calibration in Long-Horizon Tool-Using Agents paper
2026-09-14 2026-10-17 When Should LLMs Abstain? Chain-of-Self-Questioning for Selective Risk Control paper
2026-09-15 2026-10-17 SAGE: Governed Artifact Generation from Enterprise Guidelines paper
2026-09-15 2026-10-17 Bias Amplification in Multi-Agent Network: How Biased Agents Shape Opinions and Rhetoric paper
2026-09-16 2026-10-17 To Memories and Beyond: From Remembering to Knowing You across Long-Term Multimodal Personal Archives paper
2026-09-11 2026-10-17 GAVEL: Graph World Models for Verified and Efficient Long-Horizon LLM Task Planning paper
2026-09-16 2026-10-17 Closed-World Resolution Against Tool Hallucination in LLM Agents paper
2026-09-16 2026-10-17 HIL-UMI: Bringing Human-in-the-Loop Post-Training of Vision-Language-Action Models to Universal Manipulation Interface paper
2026-09-17 2026-10-17 StageGuard: Learning Stage Transitions for Long-Horizon Robot Tasks via Agentic Distillation paper
2026-09-17 2026-10-17 Origin Is All You Need: Provenance-Aware Transformers for Structural Trust-Boundary Separation paper
2026-09-17 2026-10-17 FAN: Foresight Action Normalization for Continual Adaptation of Vision-Language-Action Models paper
2026-09-18 2026-10-17 AgentVidBench: A Multi-Hop Video Question Answering Benchmark for Evaluating MLLM Agents paper
2026-09-18 2026-10-17 AtomEgo: Exploring Ego-Robot Integration for Embodied Foundation Model Pretraining paper
2026-09-18 2026-10-17 LogicTrack: Auditing Reasoning Trajectories of Large Language Models with Formal Logic Solvers paper
2026-09-18 2026-10-17 VidOmni-Bench: A Benchmark for Fine-Grained Video Understanding via Spatio-Temporal Event Verification across Complexity and Duration paper
2026-09-18 2026-10-17 AutoViewMem: Self-Configuring Orthogonal Views for Conversational Long-Term Memory paper
2026-09-18 2026-10-17 GALA: Geometry-Aware Latent Action Modeling for Vision-Language-Action Model Pretraining across Embodiments paper
2026-09-18 2026-10-17 NemotronLabs VoiceChat: An Open Full-duplex Speech-to-Speech Model with Tool Calling Capabilities paper
2026-09-18 2026-10-17 An Interpretable Memory Decision Controller for LLM Agents Based on Three-Signal Complementarity: Decoupling Confidence and Consistency paper
2026-09-18 2026-10-17 Validating, Not Sampling: Region-Level Robustness of Vision-Language and Vision-Language-Action Models paper
2026-09-14 2026-10-17 Vox-Infinity: Benchmarking the Limits of Long-Context Spoken Language Models paper
2026-09-21 2026-10-17 Trustworthy Agentic AI: Failure Modes, Mitigation Strategies, and a Lifecycle Framework for Autonomous LLM Systems paper
2026-09-19 2026-10-17 Quality over Quantity: Diversity-Aware Data Selection for Efficient Verilog Code Generation paper
2026-09-19 2026-10-17 Towards the Generalizability of Leveraging ChatGPT in APR via Self-enhancing: An Empirical Study paper
2026-09-19 2026-10-17 Discrete vs. Continuous: A Comprehensive Study of Unified Audio Understanding in LALMs paper
2026-09-19 2026-10-17 An Iterative LangGraph Agent for Text-to-SQL: Natural Language Access to the Chicago Crime Database paper
2026-09-19 2026-10-17 Beyond Similarity: Coverage-Aware Prompt Selection for Time Series Forecasting with LLMs paper
2026-09-19 2026-10-17 Enforcing Narrative Reliability and Epistemic Pacing in LLM-Driven Detective Games via Structured Knowledge Trees paper
2026-09-19 2026-10-17 From Concept Alignment to Causal Grounding: An Intervention Test of Chain-of-Thought Faithfulness paper
2026-09-19 2026-10-17 LLM-Based FORM Code Generation with Verification-Driven Fine-Tuning paper
2026-09-20 2026-10-17 STEVE: Stabilizing Textual Gradient-Based Prompt Optimization via Error-Driven Refinement and Regularized Verification paper
2026-09-20 2026-10-17 FLARE: A Full-Lifecycle Dense Supervision Paradigm for Long-Horizon Coding Agents via Generative Reward Model paper
2026-09-20 2026-10-17 ActiveArena: Benchmarking and Understanding Active Perception in Robotic Manipulation paper
2026-09-21 2026-10-17 FinRankGRPO: Optimizing LLMs for Listwise Financial Asset Ranking via Group Relative Policy Optimization paper
2026-09-21 2026-10-17 LIMIT: Less Is More for Instruction Tuning in Text-to-SQL paper
2026-09-21 2026-10-17 ChartJudgeBench: Evaluating LMM Judges for Chart-to-Code Generation paper
2026-09-21 2026-10-17 DeceptionAnalyser: A Web-Based AI Tool for Performing Structured Deception Analysis with Argumentation Schemes and LLMs paper
2026-09-21 2026-10-17 ARM: Attention with Routed-Memory for Learnable Sparse Control paper
2026-09-21 2026-10-17 A Temporal Knowledge Graph for Music Festival Lineup Forecasting paper
2026-09-21 2026-10-17 Bridge3D: Enabling Vision-Language-Action Models to See and Act in 3D paper
2026-09-21 2026-10-17 From Semantic Decisions to Feasible Trajectories: Self-Evolving LLM-Guided Optimal Control for Narrow-Space Parking paper
2026-09-21 2026-10-17 TimeLitmus: A Diagnostic Benchmark for Cross-Modal Understanding and Explanation Faithfulness in Event-Conditioned Time-Series Prediction paper
2026-09-21 2026-10-17 Coding Agents with an Obstacle-Aware Harness for Safe Robot Manipulation paper
2026-09-17 2026-10-04 TraceML: An Empirical Analysis of Human-Agent Planning in Machine Learning Development paper · Jiarui Yan et al.
2026-08-26 2026-09-29 NS-Copilot: An LLM-Driven Agent System for Autonomous Neuroscience Analysis paper · Wuche Liu et al.
2026-09-02 2026-09-28 Detecting Object Hallucinations in Large Vision-Language Models via Cross-Modal Attention Drifts and Mask-Based Verification paper · Xiao Wen et al.
2026-09-02 2026-09-28 Act More, Decide Less: Skill-Guided Adaptive Action Chunking for Long-Horizon LLM Agents paper · Yanting Yang et al.
2026-09-02 2026-09-28 DocHop: Benchmarking Out-of-domain Multi-hop Reasoning in Information-Dense Documents paper · Zhuoran Yu et al.
2026-09-02 2026-09-28 Semantics-Guided Automatic Tensorization for Multiobjective Evolutionary Algorithms: A Multi-Agent Framework paper · Zhenyu Liang et al.
2026-09-02 2026-09-28 UTP-Bench: Uncertainty-aware Travel Planning Benchmark paper · Etcharla Revanth Rao et al.
2026-09-02 2026-09-28 CivBench: A Long-Horizon Benchmark for Tool-Mediated Agents in Civilization VI paper · Austin Tudor David Andrews et al.
2026-09-02 2026-09-28 ShallowStream: Index Shallow then Answer Deep for Streaming Video Understanding paper · Jitai Hao et al.
2026-09-02 2026-09-28 Remember and Reweight: Enhancing Multi-Agent Debate with Experience Memory and Confidence Estimation paper · Xuanfa Jin et al.
2026-09-03 2026-09-28 What Do CAE Simulation Agents Really Need Beyond a Generic Harness? paper · Jiasheng Shi et al.
2026-09-03 2026-09-28 WorldReward: Reward Modeling for Camera-Conditioned World Models paper · Yibin Wang et al.
2026-09-03 2026-09-28 Integrating Crash Report Mining and LLMs for Bug Localization and Repair: An Industrial Report paper · Marcos Medeiros et al.
2026-09-03 2026-09-28 GUT: Quantifying and Optimizing the Reasoning Uncertainty of LLMs via Graph Complexity paper · Shuang Liang et al.
2026-09-04 2026-09-28 Towards a Deterministic Math Solver for Clinical Language Models paper · Felipe Ocampo Osorio et al.
2026-09-09 2026-09-27 ReactHuman: A Physics-Grounded Benchmark for Human-Like Reactive Decision-Making in Embodied Multimodal LLMs paper · Yizhan Li et al.
2026-09-09 2026-09-27 Toward Self-Adaptive Physical AI: Can LLM Agents Manage Long-Horizon Physical Tasks? paper · Varun Kaushik et al.
2026-09-11 2026-09-27 Sweet Talkers: How Query Formulation Shapes Sycophancy in Romantic Relationship Advice paper · Helena Choi et al.
2026-09-12 2026-09-27 Biomedical Reference Generation Remains Unreliable across 26 Large Language Models paper · Maxim Topaz et al.
2026-09-14 2026-09-27 EvolveTrade: Experience-Driven Policy Refinement for Self-Evolving LLM Trading Agents paper · Sehee Kim et al.
2026-09-15 2026-09-27 Not All Layers Need Tuning: Diagnosing and Directing Adaptation in Vision-Language-Action Models paper · Shahram Najam Syed et al.
2026-09-16 2026-09-27 AgentFloor: How Far Up the tool use Ladder Can Small Open-Weight Models Go? paper · Ranit Karmakar et al.
2026-05-01 2026-09-26 A Study on the Impact of Natural Language Differences in Prompts on Automatic Code Generation Using LLMs paper · Haruka Tokumasu et al.
2026-09-16 2026-09-26 no claims yet A Closed-Loop Control Architecture for Reliable Constraint Satisfaction in LLM Text Generation paper · Quan Zhou et al.
2026-09-17 2026-09-26 no claims yet Schema-Anchored Latent Reasoning for Semantic Parsing-Based Knowledge Base Question Answering paper · Guangze Gao et al.
2026-09-17 2026-09-26 no claims yet Summarization Bias: The Directional Collapse of Objective Projection into Told-Mode Labels in Large Language Models --- A Conceptual Framework and Registered Test Protocol paper · Levent Bulut
2026-09-17 2026-09-26 no claims yet OpenMAS-GCom. A Diagnostic Benchmark for Graph-enhanced Multi-Agent Systems paper · Kairui Yang et al.
2026-09-18 2026-09-26 no claims yet Samsone: A Family of Open Small Audio Language Models for On-Device Inference paper · Piotr Masztalski et al.
2026-09-18 2026-09-26 no claims yet A Sim-to-Real Integration Pipeline for Training and Deployment of Chunk-Based VLA Manipulation Policies paper · Mathilde Kappel et al.
2026-09-18 2026-09-26 no claims yet An Empirical Study and Open Testbed for Federated Fine-Tuning of Vision-Language-Action Models paper · Zhekai Duan et al.
2026-09-19 2026-09-25 no claims yet Constrained Decoding Eliminates Structural Failures in Small LLMs but Reveals a Scale-Dependent Semantic Gap paper · Akash Chavan
2026-09-20 2026-09-25 no claims yet Listen, Critique, and Refine: RL-Based Self-Refinement for Instruction-Following Speech Synthesis paper · Chee-En Yu et al.
2026-09-21 2026-09-25 no claims yet SKstars at SHROOM: Visions Agreement-Guided Ensembling of Zero-Shot and LoRA-Adapted Vision--Language Models paper · Ali Athar et al.
2026-09-21 2026-09-25 no claims yet Memory vs. Context? Influential Factors of Factual Recall in Language Models paper · Guilhem Fouilhé et al.
2026-09-21 2026-09-25 no claims yet The Copy Ceiling: An Input-Exposure Control for Ontology-Grounded Generation over Curated Corpora paper · John J. O'Hare
2026-09-21 2026-09-25 no claims yet Auto-RecSys: Harnessing Autonomous Research Agents for Industry-Scale Recommender System paper · Ming Li et al.
2026-09-10 2026-09-24 no claims yet Can LLMs Normalize Databases? A Benchmark and Multi-Agent Framework for Schema Normalization paper · Dong-Jae Koh et al.
2026-09-10 2026-09-24 no claims yet Testing Our Foundations: Citation Trends, Errors, and Emerging Hallucinations in the Computing Education Literature paper · Paul Denny et al.
2026-09-15 2026-09-24 no claims yet More Than Catastrophic Forgetting: Integrating General Capabilities For Domain-Specific LLMs paper · Chengyuan Liu et al.
2024-05-28 2026-09-23 no claims yet RefineCoder: Iterative Improving of Large Language Models via Adaptive Critique Refinement for Code Generation paper · Changzhi Zhou et al.
2025-02-13 2026-09-23 no claims yet LightPlanner: Unleashing the Reasoning Capabilities of Lightweight Large Language Models in Task Planning paper · Weijie Zhou et al.
2025-03-11 2026-09-23 no claims yet Safety Aware Task Planning via Large Language Models in Robotics paper · A. Khan et al.
2025-03-19 2026-09-23 no claims yet UA-Code-Bench: A Competitive Programming Benchmark for Evaluating LLM Code Generation in Ukrainian paper · M. Syromiatnikov et al.
2025-11-03 2026-09-23 no claims yet Multilingual Large Language Models do not comprehend all natural languages to equal degrees paper · N. Moskvina et al.
2026-02-23 2026-09-23 no claims yet Coordinated Semantic Alignment and Evidence Constraints for Retrieval-Augmented Generation with Large Language Models paper · Xin Chen et al.
2026-01-30 2026-09-23 no claims yet Sparse Reward Subsystem in Large Language Models paper
2026-02-01 2026-09-22 Answer Probing-Guided Search for Diverse Solution Exploration of LLMs paper · Yi Fang et al.
2026-08-31 2026-09-22 no claims yet Escaping Redundant Reasoning: Structure-Aware Search for Inference-Time LLMs paper · Lu Cheng
2026-09-01 2026-09-22 no claims yet Agentic ML Exploration (A-MLE) for Ads Ranking paper
2026-09-08 2026-09-22 Ensembling LLMs for AI-Augmented Cybersecurity Software Requirements Generation paper · Santiago Perez-Acuna et al.
2026-09-09 2026-09-22 Architecting the Secure AI-SOC: A Neurosymbolic Framework for Pipeline Integrity and Threat Mitigation paper · Anna Gazani et al.
2026-09-09 2026-09-22 LTLDiff: Finite Linear Temporal Logic-Guided Data Generation and Diffusion Policies for Multi-agent Robotic Manipulation paper · Chuhan Meng et al.
2026-09-10 2026-09-22 no claims yet Making Alternative Data Work: Context-Augmented LLMs for Financial Forecasting paper · Jihoon Kwon et al.
2026-09-10 2026-09-22 no claims yet MAPLE: Memory-Augmented Planning with Language and Evolution paper · Kesheng Chen et al.
2026-09-10 2026-09-22 no claims yet The Cost of Compression: A Rate-Distortion Limit on Factual Hallucination paper · Xi Vincent Wang et al.
2026-09-10 2026-09-22 no claims yet SoK: Rethinking Jailbreaking in the Era of Agentic AI: Attacks, Defenses, and Practical Consideration paper · Md Jueal Mia et al.
2026-09-11 2026-09-22 no claims yet Information Specialization and Constrained Synthesis in Multi-Agent LLM Forecasting: A Prospective Live-Study of the 2026 FIFA World Cup paper · Julian Varghese et al.
2026-09-11 2026-09-22 no claims yet Tasks over Application Manuals: Revealing Gaps in Long-Horizon Procedural Reasoning for Language Models paper · Utkarsh Soni et al.
2026-09-11 2026-09-22 no claims yet Building a Production Greek-English Speech Recognizer paper · Christos Petrocheilos et al.
2026-09-11 2026-09-22 no claims yet Domain-Specific Jargon in Large Language Models: A Comparative Analysis between General-Purpose and Specialist Models paper · Darin Keng et al.
2026-09-11 2026-09-22 Introspective Uncertainty Estimation for LLM-Based Code Generation paper · Thomas Klassert
2026-09-12 2026-09-22 no claims yet NeuroActiSep: Detecting Factual Hallucinations from Feed-Forward Neurons in a Single Pass paper · Ali Derogar Odolou et al.
2026-09-13 2026-09-22 AlgoRAG: Retrieval-Augmented Generation for Theoretical Computer Science Education -- A Comprehensive Evaluation Framework for Algorithm Analysis and Complexity Theory paper · Sushan Adhikari
2026-09-13 2026-09-22 DynSTEER: Dynamic Stage-wise Trajectory Evaluation and Execution-time Review for Agents paper · Zhichao Shi et al.
2026-09-13 2026-09-22 no claims yet Building Legal Reward Models for Grounding and Abstention paper · Rilton Franzone et al.
2026-09-13 2026-09-22 Enhancing Automated Unit Test Generation for NLP Libraries Using Large Language Models paper · Amirhossein Deljouyi et al.
2026-09-13 2026-09-22 Empirical Evaluation of Open-Source Large Language Models for Retrieval-Augmented Generation in ESG Domain paper · Motaz Saad et al.
2026-09-14 2026-09-22 Assembling the CREW: A Collaborative Multi-agent Reinforcement Learning Framework for Automated Related Work Generation paper · Hai-Dang Dang et al.
2026-09-14 2026-09-22 UDAV: Uncertainty-Driven Adaptive VLM Waypoint Planner paper · Ghazal Farhani et al.
2026-09-14 2026-09-22 no claims yet The Robot Data Factory paper · Sami Haddadin et al.
2026-09-15 2026-09-22 no claims yet VideoMM: Adaptive Macro-Micro Inference for Efficient Video MLLMs paper · Haoyu Guo et al.
2026-09-15 2026-09-22 no claims yet An Empirical Study of Counterfactual Self-Explanations in LLMs paper · Giannis Kalyvas et al.
2026-09-15 2026-09-22 no claims yet Emergence World: Adversarial Stress-Testing of Long-Horizon Multi-Agent Systems paper · Deepak Akkil et al.
2026-09-15 2026-09-22 no claims yet What Breaks Under Pruning in Smart Homes, and When? Evaluating LLM Degradation Across Architectures and Task Complexity paper · Congjing Zhang et al.
2026-09-15 2026-09-22 no claims yet HINT-Plan: Human Intention-Aware Robot Task Planning in Context-Rich Environments using Vision Language Models paper · Yuchen Liu et al.
2026-09-15 2026-09-22 SFT or RL for Tool-Calling Agents? A Controlled Study Across Data, Method, and Scale paper · Md Tahmid Rahman Laskar et al.
2026-09-15 2026-09-22 RideWay: Benchmarking Efficient Task Completion for Tool-Using Language Agents paper · Qingnuan Han et al.
2026-09-16 2026-09-22 Reinforcement Learning for Real-Time Vision-Language-Action Policies paper · Perry Dong et al.
2026-09-16 2026-09-22 Rollback the World, Keep the Reflection: Rollback-Induced Reflection for Long-Horizon LLM Agents paper · Yi Yu et al.
2026-09-16 2026-09-22 Attention Dispersion as a Diagnostic Signal for Hallucination in Large Language Models paper · Shardul P. More et al.
2026-09-16 2026-09-22 AeroWeaver: An Embodied-Agent Harness for Weaving Aerial Skills into Distributed, Adaptive Swarm Execution paper · Jiabin Lou et al.
2026-09-16 2026-09-22 M$^3$P-R1: Reinforcement Learning for Large Language Model Guided Multi-Modal Motion Planning via MIP Code Generation paper · Xingpeng Sun et al.
2026-09-16 2026-09-22 FINSKILLOPS: A Self-Evolving Multi-Agent System for SEC Filing QA paper
2026-09-17 2026-09-22 Birdwatch: Crowd Wisdom and Bridging Algorithms can Inform Understanding and Reduce the Spread of Misinformation paper · Stefan Wojcik et al.
2022-10-27 2026-09-21 ModularRSI: Modular and Generalizable Recursive Harness Self-Improvement paper
2026-09-14 2026-09-21 EvoOntology: A Self-Evolving Ontology Layer for Data Agents paper
2026-09-14 2026-09-21 Impressive paper on building recursive self-improving agent harnesses post · DAIR.AI
2026-09-21 2026-09-21 Consequence of a "publish or perish" academic mindset rather than anything serious post · Brett Hall
2026-09-21 2026-09-21 Outcome-based reputation as the incentive for a human-and-agent knowledge commons observation · Russ Miller
2026-09-21 2026-09-21 Grokipedia is dead. I'd like to rescue it, starting with scientific data post · David Siegel
2026-09-20 2026-09-21 Researchers found dopamine neurons inside LLMs post · Superman
2026-09-21 2026-09-21 ScientistTwo: Pioneering the Human Knowledge Frontier with Autonomous AI paper
2026-09-17 2026-09-20 Neural Generation of Regular Expressions from Natural Language with Minimal Domain Knowledge paper · Nicholas Locascio et al.
2016-08-09 2026-09-19 Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Task paper · Tao Yu et al.
2018-09-24 2026-09-19 Multi-modal Synthesis of Regular Expressions paper · Qiaochu Chen et al.
2019-08-09 2026-09-19 Language Models (Mostly) Know What They Know paper
2022-07-11 2026-09-19 Just Ask for Calibration: Strategies for Eliciting Calibrated Confidence Scores from Language Models Fine-Tuned with Human Feedback paper
2023-05-24 2026-09-19 Do Large Language Models Know What They Don't Know? paper
2023-05-29 2026-09-19 R-Tuning: Instructing Large Language Models to Say `I Don't Know' paper
2023-11-16 2026-09-19 Mitigating LLM Hallucinations via Conformal Abstention paper
2024-04-04 2026-09-19 Agentless: Demystifying LLM-based Software Engineering Agents paper
2024-07-01 2026-09-19 A Survey of Text-to-SQL in the Era of LLMs: Where are we, and where are we going? paper · Xinyu Liu et al.
2024-08-09 2026-09-19 RAD-Bench: Evaluating Large Language Models Capabilities in Retrieval Augmented Dialogues paper
2024-09-19 2026-09-19 RepoGraph: Enhancing AI Software Engineering with Repository-level Code Graph paper
2024-10-03 2026-09-19 OrcaLoca: An LLM Agent Framework for Software Issue Localization paper
2025-02-01 2026-09-19 XPath Agent: An Efficient XPath Programming Agent Based on LLM for Web Crawler paper · Yu Li et al.
2024-12-17 2026-09-19 LocAgent: Graph-Guided LLM Agents for Code Localization paper
2025-03-12 2026-09-19 Issue Localization via LLM-Driven Iterative Code Graph Searching paper
2025-03-28 2026-09-19 Evaluating Judges as Evaluators: The JETTS Benchmark of LLM-as-Judges as Test-Time Scaling Evaluators paper
2025-04-21 2026-09-19 SweRank: Software Issue Localization with Code Ranking paper
2025-05-07 2026-09-19 Can Prompts Rewind Time for LLMs? Evaluating the Effectiveness of Prompted Knowledge Cutoffs paper
2025-09-26 2026-09-19 NCV: A Node-Wise Consistency Verification Approach for Low-Cost Structured Error Localization in LLM Reasoning paper
2025-10-03 2026-09-19 How Language Models Conflate Logical Validity with Plausibility: A Representational Analysis of Content Effects paper
2025-10-08 2026-09-19 Autoformalizer with Tool Feedback paper
2025-10-08 2026-09-19 Defects4C: Benchmarking Large Language Model Repair Capability with C/C++ Bugs paper
2025-10-13 2026-09-19 Hard2Verify: A Step-Level Verification Benchmark for Open-Ended Frontier Math paper
2025-10-15 2026-09-19 Knowing the Facts but Choosing the Shortcut: Understanding How Large Language Models Compare Entities paper
2025-10-19 2026-09-19 RLMEval: Evaluating Research-Level Neural Theorem Proving paper
2025-10-29 2026-09-19 Do Methods to Jailbreak and Defend LLMs Generalize Across Languages? paper
2025-11-01 2026-09-19 LPFQA: A Long-Tail Professional Forum-based Benchmark for LLM Evaluation paper
2025-11-09 2026-09-19 Self-Evaluating LLMs for Multi-Step Tasks: Stepwise Confidence Estimation for Failure Detection paper
2025-11-10 2026-09-19 LocalBench: Benchmarking LLMs on County-Level Local Knowledge and Reasoning paper
2025-11-13 2026-09-19 Say It Differently: Linguistic Styles as Jailbreak Vectors paper
2025-11-13 2026-09-19 LLM-Generated Ads: From Personalization Parity to Persuasion Superiority paper
2025-12-03 2026-09-19 Single-Agent Scaling Fails Multi-Agent Intelligence: Towards Foundation Models with Native Multi-Agent Intelligence paper
2025-12-09 2026-09-19 The American Ghost in the Machine: How language models align culturally and the effects of cultural prompting paper
2025-12-13 2026-09-19 Understanding Syllogistic Reasoning in LLMs from Formal and Natural Language Perspectives paper
2025-12-14 2026-09-19 Do Multi-Agents Solve Better Than Single? Evaluating Agentic Frameworks for Diagram-Grounded Geometry Problem Solving and Reasoning paper
2025-12-18 2026-09-19 Seed-Prover 1.5: Mastering Undergraduate-Level Theorem Proving via Learning from Experience paper
2025-12-19 2026-09-19 Large language models can effectively convince people to believe conspiracies paper
2026-01-08 2026-09-19 "TODO: Fix the Mess Gemini Created": Towards Understanding GenAI-Induced Self-Admitted Technical Debt paper
2026-01-12 2026-09-19 CLM-Bench: Benchmarking and Analyzing Cross-lingual Misalignment of LLMs in Knowledge Editing paper
2026-01-24 2026-09-19 Knowledge Model Prompting Increases LLM Performance on Planning Tasks paper
2026-02-03 2026-09-19 Decomposed Prompting Does Not Fix Knowledge Gaps, But Helps Models Say "I Don't Know" paper
2026-02-04 2026-09-19 Perceived Political Bias in LLMs Reduces Persuasive Abilities paper
2026-02-20 2026-09-19 Fragile Thoughts: How Large Language Models Handle Chain-of-Thought Perturbations paper
2026-02-11 2026-09-19 Agentic LLM Planning via Step-Wise PDDL Simulation: An Empirical Characterisation paper
2026-03-06 2026-09-19 MedProbeBench: Systematic Benchmarking at Deep Evidence Integration for Expert-level Medical Guideline paper
2026-04-20 2026-09-19 CyberCertBench: Evaluating LLMs in Cybersecurity Certification Knowledge paper
2026-04-22 2026-09-19 A Metamorphic Testing Approach to Diagnosing Memorization in LLM-Based Program Repair paper
2026-04-23 2026-09-19 An Empirical Evaluation of Locally Deployed LLMs for Bug Detection in Python Code paper
2026-04-25 2026-09-19 GR-Ben: A General Reasoning Benchmark for Evaluating Process Reward Models paper
2026-05-02 2026-09-19 HEJ-Robust: A Robustness Benchmark for LLM-Based Automated Program Repair paper
2026-05-04 2026-09-19 AI-Generated Smells: An Analysis of Code and Architecture in LLM and Agent-Driven Development paper
2026-05-04 2026-09-19 Unlearners Can Lie: Evaluating and Improving Honesty in LLM Unlearning paper
2026-05-09 2026-09-19 Training-Free Cultural Alignment of Large Language Models via Persona Disagreement paper
2026-05-11 2026-09-19 CAM-Bench: A Benchmark for Computational and Applied Mathematics in Lean paper
2026-05-17 2026-09-19 Revisiting Ripple Effects in Knowledge Editing through Pressure-Aware Joint Neighborhood Optimization paper
2026-06-01 2026-09-19 Whose Norms? Disentangling Cultural and Personal Alignment in Large Language Models paper
2026-06-05 2026-09-19 Benchmarking Knowledge Editing using Logical Rules paper
2026-06-09 2026-09-19 UXBench: Measuring the Actionability of LLM-Generated UX Critiques paper
2026-06-15 2026-09-19 Misinformation Propagation in Benign Multi-Agent Systems paper
2026-06-15 2026-09-19 Skin-Deep: A Geometric Diagnostic for Alignment Fragility in Large Language Model Representations paper
2026-06-21 2026-09-19 SAKE: Software Architectural Knowledge Evaluation Benchmark for Large Language Models paper
2026-06-28 2026-09-19 An Empirical Evaluation of Prompt Injection Vulnerabilities in Large Language Models Across Multilingual and Obfuscated Attack Scenarios paper
2026-04-01 2026-09-19 Do Diagrams Help Large Language Models Reason? Evidence from Syllogistic Reasoning paper
2026-07-26 2026-09-19 On-Policy Distillation for LLM Safety: A Routing Approach to Template-Robust Realignment paper
2026-07-29 2026-09-19 Toward Meaningful Transparency for AI Chatbots: Disclosing Persuasive Intent Reduces Persuasion paper
2026-08-12 2026-09-19 From Solver Feedback to Faithful Plans: Multi-Role Reinforcement Learning for Symbolic Planning paper
2026-08-22 2026-09-19 From Memorization to Absorption: Mixed-Policy RL for Continual Knowledge Injection paper · Zhibo Hou et al.
2026-08-26 2026-09-19 HypoForge: A Self-Improving Multi-Agent Framework for Automated Hypothesis Generation and Testing via Scientific Skill Learning paper · Ziqing Qian et al.
2026-08-26 2026-09-19 Decoupling Planning and Control for Instructable Agents paper · Zineng Tang et al.
2026-08-27 2026-09-19 Boosting LLM Exploration via Weak-Model Guidance in RLVR paper · Xingyu Shen et al.
2026-08-27 2026-09-19 REINS: Refusal-Enhanced Inhibitory Steering with Sparse Autoencoder Features paper · Kai-Xuan Ding et al.
2026-08-28 2026-09-19 no claims yet CultureConverse: A Multilingual Multi-turn Simulation Harness for Culturally Grounded Assistance in East and Southeast Asia paper · Bryan Chen Zhengyu Tan et al.
2026-08-28 2026-09-19 no claims yet ReVA: A Region-Aware Visual Assistant for Visually Grounded Question Answering paper · Anoop Senthil
2026-08-27 2026-09-19 no claims yet Synthetic Worlds for Temporal Evaluation and Knowledge Updating in LLMs paper · Jonathan Zheng et al.
2026-08-31 2026-09-19 ViTAL-X: Video-Text Alignment with Cross-Modal Temporal Edits paper · Sethuraman T V et al.
2026-09-01 2026-09-19 no claims yet Aligned but Flattened: Analyzing the Trade-off between Cultural Alignment and Diversity in LLMs paper
2026-09-01 2026-09-19 PersuaRL: Reinforcement Learning-Driven Multi-Expert Selection for Persuasive Dialogue Generation in Insurance paper · Rohan Kirti et al.
2026-09-01 2026-09-19 no claims yet Evaluating Large Language Models for Forced Outage Risk Prediction: Benefits and Comparison to Machine Learning paper · Christos Petridis et al.
2026-09-02 2026-09-19 A Removal Based Approach to Improve LLM Faithfulness at Test-Time paper · Qinglan Luo et al.
2026-09-03 2026-09-19 VLA-Precision: Asymmetric Co-Bootstrapping for Efficient Real-World Online RL of Vision-Language-Action Models paper · Chenyu Su et al.
2026-09-03 2026-09-19 GRACE: Graph-Grounded Reflective Agent Copilot Engine for Expert-in-the-Loop Knowledge Expansion paper · John Seon Keun Yi et al.
2026-09-03 2026-09-19 On Epistemic Diversity in Large Language Models paper · Elisabeth Kirsten et al.
2026-09-04 2026-09-19 no claims yet Better Understanding, Better Fixes? A Study of Hallucination in LLM-based Automated Program Repair paper · Xuemeng Cai et al.
2026-09-04 2026-09-19 Leveraging Low-Level Symbolic Competences for Unsupervised Grounding in Hallucination Detection paper · Renato Vukovic et al.
2026-09-04 2026-09-19 LIBERO-RECOVER: Beyond Task Success Towards Failure Recovery in Robotic Manipulation Models paper · Lin Liu et al.
2026-09-04 2026-09-19 PRICE: A Systematic Study of LLM Adaptation Choices for Bitcoin Price Forecasting paper · Maryam Fakhari et al.
2026-09-04 2026-09-19 RoboSPA: Can VLA Models Go Beyond Simple Scenes and Short-Horizon Tasks? paper · Zhenxuan Fan et al.
2026-09-04 2026-09-19 EvoSafeHarness: Evolving Model- and Domain-Specific Harnesses for Securing Agents paper · Nanxi Li et al.
2026-09-05 2026-09-19 SpecCoder: Specification-Aware Code Generation with Curriculum Dual-Task Reinforcement Learning paper · Yixuan Li et al.
2026-09-05 2026-09-19 STQA: A Benchmark for Stock-Focused Tabular Question Answering over Historical and Forecasted Data paper · Baoxu An et al.
2026-09-05 2026-09-19 Counterfactual Tests for Measuring Chain-of-Thought Faithfulness in Visual Language Models paper · Bayar Menzat et al.
2026-09-06 2026-09-19 NutriBench-Kitchen: Benchmarking Embodied AI for Nutrition Management paper · Yulin Wei et al.
2026-09-07 2026-09-19 In-Place Instruction Following in Diffusion Language Models paper · Zheng Nie et al.
2026-09-07 2026-09-19 TAD: Token-Adaptive Contrastive Decoding with Confidence-Guided Gating for Hallucination Mitigation in Large Audio-Language Models paper · Heyu Chang et al.
2026-09-07 2026-09-19 Beyond Fluent Generation: A CPU Reliability Benchmark for MCP-Style Tool Calling in Sub-2B Small Language Models for Edge Deployment paper · Abrar Shahriar Qurat-Ul-Ain Mastoi
2026-09-07 2026-09-19 CIT-CAD: Constraint Intent Tree-based CAD Code Generation and Verification paper · Yali Du et al.
2026-09-07 2026-09-19 Popular Knowledge Propagates More Errors in LLM Knowledge Updating paper · Yuji Zhang et al.
2026-09-08 2026-09-19 Less Is Personal: Learning Minimal Sufficient User Profiles for Personalized Language Models paper · Minghang Liu et al.
2026-09-08 2026-09-19 Towards Embodied Air-Ground Cooperative Object Search: Benchmark, Dataset and Agentic Method paper · Boao Yu et al.
2026-09-08 2026-09-19 Safe Task Planning with Long-Term Graph Memory for Embodied Agents paper · Siyuan Li et al.
2026-09-08 2026-09-19 AgentGrad: Intervention-guided Prompt Optimization for Multi Agent Systems paper · Jaewon Chu et al.
2026-09-08 2026-09-19 Closing the Consistency Gap: Self-Evolving Agents That Learn to Stay on Course paper · Evelyn Duesterwald et al.
2026-09-08 2026-09-19 DSE-VTG: Dual-Side Enhancement for Training-Free Video Temporal Grounding paper · Zhuo Cao et al.
2026-09-08 2026-09-19 Experience Funnel: A State-Policy Alternating Loop for Self-Evolving Agents paper · Wenbo Gao et al.
2026-09-08 2026-09-19 Evaluating and Improving Evidence-Grounded Fact-Checking in LLMs via Multi-Round Evidence Ablation paper · Xingyu Deng et al.
2026-09-08 2026-09-19 Measuring LLM Sycophancy under Sustained Multi-Turn Pressure paper · Leyuan Tang et al.
2026-09-08 2026-09-19 MLLMs Hallucinate when Information Distribution Drifts in Synergy Heads paper · Meng'en Qin et al.
2026-09-05 2026-09-19 An Experimental Evaluation of Multimodal Prompt Injection Attacks on Agentic AI Frameworks paper · Viet K. Nguyen et al.
2026-09-08 2026-09-19 Benchmarking Agentic HLS Design Tasks With HLS-Eval paper · Stefan Abi-Karam et al.
2026-09-08 2026-09-19 SEA-SpeechBench: A Large-Scale Multitask Benchmark for Speech Understanding Across Southeast Asia paper · Jingyi Liao et al.
2026-09-09 2026-09-19 Beyond Accuracy: ARIA-Rubrics for Evaluating Audio Reasoning in Large Audio Language Models paper · Yupei Li et al.
2026-09-09 2026-09-19 When Auditors Fabricate: Batch-Size Degradation and Confident Hallucination in LLM Detection of Planted Document Contamination paper · Karan Parekh et al.
2026-09-09 2026-09-19 LexAgentHallu: A Hierarchical Benchmark for Profiling Hallucinations in Legal Agents paper · Yujin Zhou et al.
2026-09-09 2026-09-19 Keep Evaluation Fair: Detecting Data Leakage in Code Generation Benchmarks via Membership Inference Attacks paper · Dongdong Zhao et al.
2026-09-09 2026-09-19 Can We Trust Video Hallucination Detectors? VidHalLoc for Evaluating the Evaluators paper · Xinyu Chen et al.
2026-09-09 2026-09-19 Guaranteeing Faithful Evidence Extraction in Speculative Retrieval-Augmented Generation paper · Quentin Signé et al.
2026-09-09 2026-09-19 ConvMem: Convolutional Memory for Long-Context Reasoning paper · Hongming Zhang et al.
2026-09-09 2026-09-19 Programmable World Model paper · Zheng-Hui Huang et al.
2026-09-09 2026-09-19 Multi-Faceted Evaluation and Mitigation of Emotion Hallucinations in MLLMs paper · Bowen Zeng et al.
2026-09-10 2026-09-19 NovGauge: A Fine-Grained Benchmark for Diagnosing LLMs' Capability in Paper Novelty Assessment paper · Guoqiang Zhang et al.
2026-09-10 2026-09-19 no claims yet OmniHallu: Unified Hallucination Detection for Cross-Modal Comprehension and Generation in Multimodal Large Language Models paper · Jianjiang Yang et al.
2026-09-10 2026-09-19 AudioICL-Bench: A Benchmark for Large Audio Language Model In-Context Learning paper · Jia‐Hung Chen et al.
2026-09-10 2026-09-19 Ecdysis: Efficient and Effective Training of Runtime Harnesses for LLM Agents paper · Ruiqing Yue et al.
2026-09-10 2026-09-19 ORCH: Organizational Principles Enable Collective Intelligence in Embodied AI paper · Zhengran Ji et al.
2026-09-10 2026-09-19 Domain-Specific Hallucination Detection in Large Language Models paper · Varun Teja Chundru et al.
2026-09-10 2026-09-19 Repair Before Reinforce: Context-Augmented Knowledge Graph Reasoning for Multi-Hop Question Answering paper · Tharaka D. Fonseka et al.
2026-09-10 2026-09-19 Beyond Vector Similarity: Hierarchical Context-Aware Graph RAG vs Standard RAG in Enterprise Code Migration paper · Nilesh Jaiswal et al.
2026-09-11 2026-09-19 Earth-Agent-Pro: Towards Real-World Full-Chain Earth Observation with Agents paper · Zhutao Lv et al.
2026-09-11 2026-09-19 Bridging Thought and Action: Taming Long-Horizon Instability in Open-Source LLM Agents with a MetaTool-Enhanced ROS Framework paper · Kazi Abrar Mahmud et al.
2026-09-11 2026-09-19 The Deception Delta: Adversarial Evaluation of LLM-Based Smart Contract Bytecode Forensics paper · Timo Schefold
2026-09-12 2026-09-19 no claims yet Grounded in Sound: Reinforcement Learning with a Frozen Acoustic Judge to Curb ASR Insertion Hallucinations paper · Tingzhen Xiong et al.
2026-09-13 2026-09-19 EMR: Self-Evolving Medical Multi-Agent System via Experience Mining and Reuse paper · Dongsheng Shi et al.
2026-09-14 2026-09-19 HarnessVLN: Unifying Training-Free Embodied Navigation through an Agent Harness paper · Yang Chen et al.
2026-09-14 2026-09-19 Adversarial Testing of Automated Program Repair Agents for Security Vulnerabilities paper · Fares Trad et al.
2026-09-14 2026-09-19 Stellar Colosseum: A Many-Agent Harness for Long-Horizon Research in Mathematics and Theoretical Computer Science paper · Honghao Lin et al.
2026-09-14 2026-09-19 Universal Defenses for Tool-Integrated LLM Agents Against Adversarial Attacks paper · Xiaoyan Li et al.
2026-09-14 2026-09-19 Spurious Tool Use: When RL Agents Learn the Wrong Reason to Act paper · Yiwei Yang et al.
2026-09-14 2026-09-19 A light-touch AI literacy intervention helps protect against AI political persuasion paper
2026-09-14 2026-09-19 SAVOR: Self-Aware Visual Grounding via Confidence-Calibrated Reinforcement Learning for Multimodal Hallucination Mitigation paper · Zixiu Ding et al.
2026-09-15 2026-09-19 EgoPathBench: Evaluating Zero-Shot Egocentric Waypoint Decision-Making in Vision-Language Models paper · Yang Zhao et al.
2026-09-15 2026-09-19 What Do Hallucinations Reveal About Multimodal Reasoning? Diagnosing Visual Grounding Failures via Contrastive Decoding Probes paper · Zhipeng Zhao et al.
2026-09-15 2026-09-19 ViD: Vision-Dominant Gender Bias Mitigation for Large Vision-Language Models paper · Zhipeng Zhao et al.
2026-09-15 2026-09-19 Video-HolmesV2: Can MLLMs Reason with Spatio-Temporal Audio-Visual Evidence in Long Videos? paper · Zhaoyang Wei et al.
2026-09-15 2026-09-19 Semantic-Spatial Agreement Verification for Mitigating Object Hallucination in Multimodal Large Language Models paper · Ziheng Ren et al.
2026-09-15 2026-09-19 Rethinking Multi-Agent Collaboration: When More Is Less paper
2026-09-17 2026-09-19 SoL-Pi: Recursively Scaling Auto-Research Loops for Efficient Agent Harness paper · Haozhe Liu et al.
2026-09-17 2026-09-19 Automatic XPath generation agents for vertical websites by LLMs paper · Huang et al.
2025-06-18 2026-09-19 Wrapper Induction: Efficiency and Expressiveness paper · Nicholas Kushmerick
2000-04-01 2026-09-19 FlashExtract: A Framework for Data Extraction by Examples paper · Vu Le et al.
2014-06-01 2026-09-19 From Examples to Patterns: LLM-Generated Regular Expressions for Entity Extraction in Czech Clinical Texts paper · Petr Zelina
2024-12-01 2026-09-19 SemRegex: A Semantics-Based Approach for Generating Regular Expressions from Natural Language Specifications paper · Zexuan Zhong et al.
2018-10-01 2026-09-19 Cooperative Inverse Reinforcement Learning paper · Dylan Hadfield-Menell et al.
2016-06-09 2026-09-18 no claims yet The Off-Switch Game paper · Dylan Hadfield-Menell et al.
2016-11-24 2026-09-18 no claims yet Measuring Progress on Scalable Oversight for Large Language Models paper · Samuel R. Bowman et al.
2022-11-04 2026-09-18 no claims yet Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervision paper · Collin Burns et al.
2023-12-14 2026-09-18 no claims yet Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training paper · Evan Hubinger et al.
2024-01-10 2026-09-18 no claims yet On the Conversational Persuasiveness of Large Language Models: A Randomized Controlled Trial paper · Francesco Salvi et al.
2024-03-21 2026-09-18 no claims yet CoER: Defending against Adaptive Indirect Prompt Injection via Adversarial Co-Evolution and Refinement paper
2026-09-07 2026-09-18 Thinking with Looped Flows paper · Ayhan Suleymanzade et al.
2026-09-10 2026-09-18 no claims yet Evaluation of MLLM-Agnostic Plug-and-Play Keyframe Selection Methods for Long Video Understanding paper
2026-09-04 2026-09-18 TimeThink: Eliciting Compositional Reasoning in Timeseries Large Language Models paper
2026-09-11 2026-09-18 DARE: Dialectical Agentic Reasoning for Structured Knowledge Fact Checking paper
2026-09-12 2026-09-18 E2A-Bench: Benchmarking Evidence-to-Action Reliability in Financial Chart Reasoning paper
2026-09-13 2026-09-18 Theseus in the Graph: Towards Traceable Multi-Hop Graph Navigation paper
2026-09-13 2026-09-18 Fabrication After Tool Failure: Tool-Augmented Agents Assert Values Their Tools Did Not Return paper
2026-09-13 2026-09-18 Efficiency Hallucination: Formalizing and Measuring Behavioral Calibration in LLM-Based Code Optimization paper
2026-09-13 2026-09-18 ActGuard: Pre-execution Action Auditing against Indirect Prompt Injection in LLM Agents paper
2026-09-14 2026-09-18 MTAC-IFBench: Benchmarking Instruction-Following in Multi-Turn Agentic Coding paper
2026-09-14 2026-09-18 When the Wrong Key Wins: Understanding and Detecting Hallucinations in LLMs paper
2026-09-14 2026-09-18 MarKey: Marginal Utility Guided Greedy Keyframe Selection for Long Video Understanding paper
2026-09-14 2026-09-18 VideoScout: Learning Agentic Active Exploration with Adaptive Reasoning Pacing for Long Video Understanding paper
2026-09-14 2026-09-18 Look Before You Leap: Factual Decoding with Internal Attribution Signals paper
2026-09-14 2026-09-18 AlgoEvo: Self-Evolving Agentic Search for Automated Algorithm Discovery paper
2026-09-14 2026-09-18 AgenTeeth: A Model-Agnostic Framework for Suppressing Hallucination in Frozen Vision-Language Models on Dental X-Rays via Tool Evidence Injection paper
2026-09-15 2026-09-18 The 'godfather of AI' reveals the only way humanity can survive superintelligent AI post · Matt Egan (CNN Business)
2025-08-13 2026-09-18 Hashimoto's rule for AI agents is that every mistake becomes a permanent fix post · Alex Veremeyenko
2026-09-09 2026-09-18 Cache-to-Cache: Direct Semantic Communication Between Large Language Models paper · Tianyu Fu et al.
2025-10-03 2026-09-17 no claims yet Embodied-Navigator: Point, Think, Memorize, and Align for Efficient Navigation paper
2026-08-18 2026-09-15 Do Large Language Models Play Six Degrees of Separation? Measuring Topological Compression in Long-Context Manifolds paper
2026-08-18 2026-09-15 Mechanistic Interpretability of Structure-Aware Numerical Reasoning in LLaMA 3.1 8B paper
2026-08-19 2026-09-15 Bayesian Partner Modelling enables Adaptive Replanning for LLM Coordination paper
2026-08-19 2026-09-15 DART-SD: Diamond-topology Aware Retrieval and Tuning for Self-Distillation of Multi-Turn Tool-Calling Agents paper
2026-08-19 2026-09-15 From Storage to Access: Verifiable Activation of Parametric Knowledge in LLMs via Explicit Priming and Implicit Reasoning paper
2026-08-19 2026-09-15 SPADE: Self-Play in Adaptive Synthetic Executable Environments paper
2026-08-19 2026-09-15 Hype Meets Reality: Large Language Models as Mutators in Search-based Automated Program Repair of Simulink-Stateflow Models paper
2026-08-19 2026-09-15 PEA-DPO: Perception-Enhanced Alignment Direct Preference Optimization for MLLMs Alignment paper
2026-08-20 2026-09-15 World-Model-Grounded LLM Planning for AUV and ASV Navigation Near Offshore Wind Farms paper
2026-08-20 2026-09-15 SAPO: Single-Rollout Autoregressive Policy Optimization for Agentic Reinforcement Learning paper
2026-08-20 2026-09-15 Enhancing Localized Reasoning for Long Video Understanding via Efficient Segment-to-Video Supervision paper
2026-08-21 2026-09-15 Designing a Robust LLM-Based Evaluation System for Agentic AI in Drug Discovery Through Human Alignment paper
2026-08-21 2026-09-15 Small Reasoning Models are Instruction Followers in Function Calling paper
2026-08-23 2026-09-15 Benchmarking the Titans: A Multi-Dimensional Empirical Evaluation of LLM Code Generation Quality in the .NET Ecosystem paper
2026-08-23 2026-09-15 Beyond Factual Knowledge: Benchmarking and Learning Step-Level Procedural Rule Reasoning in Large Language Models paper
2026-08-24 2026-09-15 Execution-Anchored Hallucination Calibration Reranking for Verilog Code Generation paper
2026-08-24 2026-09-15 SRPO: Self-Reflective Policy Optimization for Long-Horizon Reasoning paper
2026-08-24 2026-09-15 SWE Refactor Bench: Can Coding Agents Complete a Long-Horizon, Whole-Repository Stack Migration? paper
2026-08-24 2026-09-15 EXAM$^2$: $\underline{Ex}tending$ $\underline{A}udio$ $Understanding$ $in$ $\underline{M}ultilingual$ $and$ $\underline{M}ultimodal$ $Analysis$ paper
2026-08-24 2026-09-15 Language Models are Few-Shot Learners paper · Tom B. Brown et al.
2020-05-28 2026-09-14 no claims yet WebGPT: Browser-assisted question-answering with human feedback paper · Reiichiro Nakano et al.
2021-12-17 2026-09-14 no claims yet ReAct: Synergizing Reasoning and Acting in Language Models paper · Shunyu Yao et al.
2022-10-06 2026-09-14 no claims yet Voyager: An Open-Ended Embodied Agent with Large Language Models paper · Guanzhi Wang et al.
2023-05-25 2026-09-14 no claims yet Multi-Agent Collaboration: Harnessing the Power of Intelligent LLM Agents paper · Yashar Talebirad et al.
2023-06-05 2026-09-14 no claims yet InterCode: Standardizing and Benchmarking Interactive Coding with Execution Feedback paper · John Yang et al.
2023-06-26 2026-09-14 no claims yet DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines paper · Omar Khattab et al.
2023-10-05 2026-09-14 no claims yet Darwin Godel Machine: Open-Ended Evolution of Self-Improving Agents paper · Jenny Zhang et al.
2025-05-29 2026-09-14 no claims yet GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning paper · Lakshya A Agrawal et al.
2025-07-25 2026-09-14 no claims yet Recursive Language Models paper · Alex L. Zhang et al.
2025-12-31 2026-09-14 no claims yet Meta-Harness: End-to-End Optimization of Model Harnesses paper · Yoonho Lee et al.
2026-03-30 2026-09-14 no claims yet Continual Harness: Online Adaptation for Self-Improving Foundation Agents paper · Seth Karten et al.
2026-05-11 2026-09-14 no claims yet OpenJarvis: Personal AI, On Personal Devices paper · Jon Saad-Falcon et al.
2026-05-16 2026-09-14 no claims yet Prime Agent: A Self-Improving RLM Harness paper · Seth Karten et al.
2026-08-24 2026-09-14 no claims yet The Last AI Built by Humans: Toward Genuine Recursive Self-Improvement paper · Yi Duan et al.
2026-09-10 2026-09-13 Measuring AI Ability to Complete Long Software Tasks paper · Thomas Kwa et al.
2025-03-18 2026-09-12 SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering paper · John Yang et al.
2024-05-06 2026-09-11 Evaluating AGENTS.md: Are Repository-Level Context Files Helpful for Coding Agents? paper · Thibaud Gloaguen et al.
2026-02-12 2026-09-11 Code as Agent Harness paper · Xuying Ning et al.
2026-05-18 2026-09-11 no claims yet Harness-Bench: Measuring Harness Effects across Models in Realistic Agent Workflows paper · Yilun Yao et al.
2026-05-27 2026-09-11 Self-Harness: Harnesses That Improve Themselves paper · Hangfan Zhang et al.
2026-06-08 2026-09-11 Harness engineering for coding agent users post
2026 2026-09-11 Maintainability sensors for coding agents post
2026 2026-09-11 I Improved 15 LLMs at Coding in One Afternoon. Only the Harness Changed. post · Can Bölük
2026-02-12 2026-09-11 HAL GAIA Leaderboard (Holistic Agent Leaderboard, Princeton) post · Princeton HAL team
2026 2026-09-11 My AI Adoption Journey – Mitchell Hashimoto post
2026 2026-09-11 Improving Deep Agents with harness engineering vendor-doc
2026 2026-09-11 Agentic Harness Engineering: The Operating System for Machine Intelligence post · Adnan Masood
2026-06-27 2026-09-11 Harness engineering: leveraging Codex in an agent-first world vendor-doc · Ryan Lopopolo
2026-02-11 2026-09-11 no claims yet Harness Engineering — Agent = Model + Harness: The 6-Layer Production Playbook post · Unattributed (independent synthesis)
2026-08-01 2026-09-11 Hallucination as Context Drift: Synchronization Protocols for Multi-Agent LLM Systems paper · Carson Rodrigues
2026-06-19 2026-09-09 What Guides the Agent? Adjudicating Unauthorized Behavior via Localizing Behavior-Guiding Instructions paper
2026-08-25 2026-09-09 ACE: A Self-Correcting Agentic Canvas Editor for Multi-Slide Presentation Automation paper
2026-08-25 2026-09-09 Rubrics as Visual-Repair Context for Self-Evolving UI-to-Code Generation paper
2026-08-25 2026-09-09 When Do Supervised UQ Ensembles Improve LLM Hallucination Detection? A Robustness Study paper
2026-08-25 2026-09-09 Lost in Speech: Trilingual Spoken Hallucination Detection Across Audio and Transcripts paper
2026-08-25 2026-09-09 Targeting the Attention Heads Behind Object Hallucination in LLaVA paper
2026-08-25 2026-09-09 Mitigating LLM sycophancy with RL-based fine-tuning: Bayesian Truth Serum approach paper
2026-08-26 2026-09-09 Video-IFBench: Evaluating Instruction Following of Multimodal LLMs in Video Understanding Scenarios paper
2026-08-26 2026-09-09 Overview of SHROOM-Visions 2026: A Shared Task on Hallucination Detection in Large Vision-Language Models paper
2026-08-26 2026-09-09 AI Slop and Hallucinations in Vulnerability Assessment: A Survey on Reasoning Failures and Trustworthy Mitigation paper
2026-08-26 2026-09-09 XREPOTEST: Benchmarking Multilingual Repository-Level Unit Test Generation for Large Language Models paper
2026-08-26 2026-09-09 SciMIF: Understanding Multimodal Instruction Following in Scientific Domains paper
2026-08-26 2026-09-09 VISA: Agentic Self-Evolving Data Synthesis for Multimodal Instruction Following paper
2026-08-26 2026-09-09 Benchmarking AI Agents for Hardware Design Automation via MCP Tool Calling paper
2026-08-25 2026-09-09 Knowledge-Verified Emergent Deception in LLM Agents Under Conflicting Incentives paper
2026-08-26 2026-09-09 Sycophancy Suppression Can Impair Rational Updating: Anti-Sycophancy Should Preserve the Ability to Update paper
2026-08-27 2026-09-09 Unsaid, Unsafe? Implicit Security Obligations in LLM-Based RTL Code Generation paper
2026-08-27 2026-09-09 Prediction of Prediction (PoP): Inter-Layer Activation Fusion for Single-Pass Hallucination Detection in Large Language Models paper
2026-08-27 2026-09-09 ROPE: Routed Origin Policy Enforcement against Indirect Prompt Injection paper
2026-08-27 2026-09-09 The Calls are Coming from Inside the Model: Investigating Probe-based Detection of Tool-Calling Errors in LLMs paper
2026-08-27 2026-09-09 Dynamic Alignment Compensation for Hallucination Mitigation in Large Vision-Language Models paper
2026-08-28 2026-09-09 LongPIBench: A Long-Context Benchmark for Prompt Injection paper
2026-08-28 2026-09-09 Learning to Use Tools: Reinforcement Learning for Tool-Integrated Mathematical Reasoning paper
2026-08-28 2026-09-09 ContextPilot: Teaching Agents for Proactive Context Management via Fine-grained RL paper
2026-08-28 2026-09-09 Evaluating the Hidden Costs of Personalization in Large Language Models paper
2026-08-28 2026-09-09 Towards Fully Automated Medical Imaging Code Generation via Validation-based Context Engineering paper
2026-08-29 2026-09-09 EviAnchor: Mitigating Hallucinations in Large Vision-Language Models via Regional Visual Evidence Compensation paper
2026-08-29 2026-09-09 How Identity and Opinion Shape Political Sycophancy in LLMs paper
2026-08-29 2026-09-09 Detecting and Repairing Hallucinations in Retrieval-Augmented Generation paper
2026-08-29 2026-09-09 Cross-Relational Preference Learning for Better LLM Instruction Following paper
2026-08-29 2026-09-09 Think, Look, and Revise: Inconsistency-Aware Visual Self-Correction in MLLMs paper
2026-08-29 2026-09-09 Evaluating Tiny Recursive Models Across Training for Code Generation paper
2026-08-29 2026-09-09 Agent Zero Memory: Provenance-Aware Long-Term Memory for LLM Agents paper
2026-08-30 2026-09-09 Hallucination Mitigation for Large Vision-Language Models via Implicit Feature Stabilization paper
2026-08-30 2026-09-09 SpanCalib-VLM: Calibrated Hallucination Span Detection in Vision-Language Models paper
2026-08-30 2026-09-09 Reachability-Based Capability Confinement for LLM Agents under Indirect Prompt Injection paper
2026-08-30 2026-09-09 CAST: Critique-Aware Supervision for Training Reliable Long-Horizon Tool-Calling Agents paper
2026-08-31 2026-09-09 SIR: Self-improving Red-teaming for Compute Use Agents paper
2026-08-31 2026-09-09 DSEffi-Bench: Demystifying Large Language Models' Capability in Efficient Data Science Code Generation paper
2026-08-31 2026-09-09 ECLIPSE: Self-Evolving Stealthy Prompt Injection Attack against Long-Horizon Agentic Systems paper
2026-08-31 2026-09-09 VisER: Visual Evidence and Reliance for Object Hallucination Detection in LVLMs paper
2026-08-31 2026-09-09 SingProbe Technical Report paper
2026-08-31 2026-09-09 Likelihood-Constrained Acoustic Reranking for Training-Free Hallucination Mitigation in LLM-Based ASR paper
2026-08-31 2026-09-09 Stick to What You Know: A Study of Knowledge-Aligned Supervised Fine-Tuning paper
2026-08-31 2026-09-09 Sycophantic Agreement Transfers with Neutral Data via Contrastive Preference Optimization paper
2026-08-31 2026-09-09 Do Multimodal LLMs See Before They Read? Diagnosing Contextual Sycophancy paper
2026-08-30 2026-09-09 Beyond Language Priors: Diagnosing and Fixing Visual-Origin Hallucinations in Multimodal LLM paper
2026-08-31 2026-09-09 Towards a Belief-Based World Model for LLM Agents paper
2026-08-31 2026-09-09 The Privacy-Hallucination Tradeoff in Differentially Private Language Models paper
2026-08-31 2026-09-09 WiseSpec: Requirements-Driven Agents for Code Generation paper
2026-09-01 2026-09-09 Can Large Language Models Forecast What Researchers Study Next? paper
2026-09-01 2026-09-09 VIBE-Bench: Evaluating Personalized Large Language Models When Profiles Don't Mean Preferences paper
2026-09-01 2026-09-09 Calibration is the Bottleneck: An Action-Class Diagnostic of Multi-Turn Tool-Calling paper
2026-09-01 2026-09-09 Reliability Challenges in Diffusion Vision-Language Models paper
2026-09-01 2026-09-09 InSight: A Benchmark for Agentic Claim Verification in Interactive Visualizations paper
2026-09-01 2026-09-09 CAPTURE: Disentangling Preference Drift from Memory Poisoning in Personalized LLM Agents paper
2026-09-02 2026-09-09 Improving Health Literacy through Lay Summarization of Radiological Reports: An Evaluation of BioNER and Retrieval-Augmented Generation paper
2026-09-02 2026-09-09 From Tokens to Semantics: Leveraging Complementary Signals for Hallucination Detection in Black-Box LLMs paper
2026-09-02 2026-09-09 RVSD: Retrieval Vision Sparse Decoding for Mitigating Visual Hallucinations in Large Vision-Language Models paper
2026-09-02 2026-09-09 Compound Prompt Constraints in LLM Code Generation: A Factorial Study of Format, Persona, and Urgency paper
2026-09-02 2026-09-09 Refusing the Impossible: A Taxonomy and Benchmark for Code Hallucination in Large Language Models paper
2026-09-03 2026-09-09 HalluPeer: A Taxonomy-driven Benchmark for Detecting Hallucinations in Scientific Peer Reviews paper
2026-09-03 2026-09-09 KC-Bench: A Dynamic Interactive Benchmark for Evaluating Knowledge Conflicts in LLM Agents paper
2026-09-03 2026-09-09 Beyond Retrieval: Progressive Latent Memory Evolution for Streaming Video Understanding paper
2026-09-03 2026-09-09 The new rules of context engineering for Claude 5 generation models vendor-doc · Anthropic
2026 2026-09-08 FARCA: Fact-Aligned Reliability-Aware Credit Assignment for Reinforcement Learning with Factual Supervision paper
2026-08-25 2026-09-07 From Passive Response to Proactive Correction: Enhancing LLM Robustness Against Input Fact Perturbations paper
2026-08-26 2026-09-07 LongGuard: Mechanistic Analysis and Training-Free Mitigation of Long-Context Failure in Safety Guardrails paper
2026-08-27 2026-09-07 Fine-Grained Multi Image Object Hallucination Benchmark paper
2026-08-31 2026-09-07 LOCI: A Locator-Critic with Refinement Loop paper
2026-08-31 2026-09-07 Compile, Don't Memorize: A Context Compilation Architecture (CCA) for In-Context Learning paper
2026-09-01 2026-09-07 Harness Engineering in LLM Tool Use via Agent-Native Reusable Tool Primitives paper
2026-09-01 2026-09-07 Does Playing it Safe Count as Faithfulness? Reassessing LVLM Hallucination Mitigation Methods paper
2026-09-01 2026-09-07 Large Language Models in Resolving Contextual Knowledge Conflicts paper
2026-09-02 2026-09-07 The Economics of Recursive Self-Improvement paper · Tom Cunningham et al.
2026-07-13 2026-09-07 On OpenAI's research-acceleration disclosure — the measured variables are all inputs post · Cheryl Wu
2026-09-06 2026-09-07 Evaluating Large Language Models Trained on Code paper · Mark Chen et al.
2021 2026-09-04 This source: Evaluating Large Language Models Trained on Code How much the field cites it — very heavily cited in the last 12 months 1000+ in the last 12 months · 11293 total published 2021 checked 2026-09-04 count capped at 1000 by the fetch click for Semantic Scholar Forecasting Future World Events with Neural Networks paper · Andy Zou et al.
2022 2026-09-04 This source: Forecasting Future World Events with Neural Networks How much the field cites it — steadily cited in the last 12 months 33 in the last 12 months · 68 total published 2022 checked 2026-09-04 click for Semantic Scholar Deception Abilities Emerged in Large Language Models paper · Thilo Hagendorff
2023 2026-09-04 This source: Deception Abilities Emerged in Large Language Models How much the field cites it — heavily cited in the last 12 months 75 in the last 12 months · 191 total published 2023 checked 2026-09-04 click for Semantic Scholar Exploring Large Language Models for Communication Games: An Empirical Study on Werewolf paper · Yuzhuang Xu et al.
2023 2026-09-04 This source: Exploring Large Language Models for Communication Games: An Empirical … How much the field cites it — heavily cited in the last 12 months 59 in the last 12 months · 312 total published 2023 checked 2026-09-04 click for Semantic Scholar FireAct: Toward Language Agent Fine-tuning paper · Baian Chen et al.
2023-10-09 2026-09-04 This source: FireAct: Toward Language Agent Fine-tuning How much the field cites it — heavily cited in the last 12 months 101 in the last 12 months · 252 total published 2023 checked 2026-09-04 click for Semantic Scholar Approaching Human-Level Forecasting with Language Models paper · Danny Halawi et al.
2024 2026-09-04 This source: Approaching Human-Level Forecasting with Language Models How much the field cites it — heavily cited in the last 12 months 76 in the last 12 months · 125 total published 2024 checked 2026-09-04 click for Semantic Scholar LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code paper · Naman Jain et al.
2024 2026-09-04 This source: LiveCodeBench: Holistic and Contamination Free Evaluation of Large Lan… How much the field cites it — very heavily cited in the last 12 months 1000+ in the last 12 months · 2073 total published 2024 checked 2026-09-04 count capped at 1000 by the fetch click for Semantic Scholar TICKing All the Boxes: Generated Checklists Improve LLM Evaluation and Generation paper · Jonathan Cook et al.
2024-10-04 2026-09-04 This source: TICKing All the Boxes: Generated Checklists Improve LLM Evaluation and… How much the field cites it — steadily cited in the last 12 months 33 in the last 12 months · 61 total published 2024 checked 2026-09-04 click for Semantic Scholar AI-Generated Code Is Not Reproducible (Yet): An Empirical Study of Dependency Gaps in LLM-Based Coding Agents paper · Bhanu Prakash Vangala et al.
2025-12-26 2026-09-04 Stop Means Stop: Measuring and Repairing the Enforcement Gap in Agent-Framework Control Primitives paper · Sajjad Khan
2026-07-15 2026-09-04 Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks paper · Patrick Lewis et al.
2020 2026-09-02 This source: Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks How much the field cites it — very heavily cited in the last 12 months 1000+ in the last 12 months · 17840 total published 2020 checked 2026-09-04 count capped at 1000 by the fetch Asleep at the Keyboard? Assessing the Security of GitHub Copilot's Code Contributions paper · Hammond Pearce et al.
2021 2026-09-02 This source: Asleep at the Keyboard? Assessing the Security of GitHub Copilot's Cod… How much the field cites it — very heavily cited in the last 12 months 413 in the last 12 months · 952 total published 2021 checked 2026-09-04 click for Semantic Scholar TruthfulQA: Measuring How Models Mimic Human Falsehoods paper · Stephanie Lin et al.
2021 2026-09-02 This source: TruthfulQA: Measuring How Models Mimic Human Falsehoods How much the field cites it — very heavily cited in the last 12 months 1000+ in the last 12 months · 3851 total published 2021 checked 2026-09-04 count capped at 1000 by the fetch Training Verifiers to Solve Math Word Problems paper · Karl Cobbe et al.
2021 2026-09-02 This source: Training Verifiers to Solve Math Word Problems How much the field cites it — very heavily cited in the last 12 months 1000+ in the last 12 months · 10385 total published 2021 checked 2026-09-04 count capped at 1000 by the fetch click for Semantic Scholar Chain-of-Thought Prompting Elicits Reasoning in Large Language Models paper · Jason Wei et al.
2022 2026-09-02 This source: Chain-of-Thought Prompting Elicits Reasoning in Large Language Models How much the field cites it — very heavily cited in the last 12 months 1000+ in the last 12 months · 21548 total published 2022 checked 2026-09-04 count capped at 1000 by the fetch no claims yet Impact of Pretraining Term Frequencies on Few-Shot Reasoning paper · Yasaman Razeghi et al.
2022 2026-09-02 This source: Impact of Pretraining Term Frequencies on Few-Shot Reasoning How much the field cites it — steadily cited in the last 12 months 15 in the last 12 months · 191 total published 2022 checked 2026-09-04 click for Semantic Scholar Do Users Write More Insecure Code with AI Assistants? paper · Neil Perry et al.
2022 2026-09-02 This source: Do Users Write More Insecure Code with AI Assistants? How much the field cites it — very heavily cited in the last 12 months 200 in the last 12 months · 430 total published 2022 checked 2026-09-04 click for Semantic Scholar Large Language Models Struggle to Learn Long-Tail Knowledge paper · Nikhil Kandpal et al.
2022 2026-09-02 This source: Large Language Models Struggle to Learn Long-Tail Knowledge How much the field cites it — very heavily cited in the last 12 months 203 in the last 12 months · 730 total published 2022 checked 2026-09-04 Ignore Previous Prompt: Attack Techniques For Language Models paper · Fábio Perez et al.
2022 2026-09-02 This source: Ignore Previous Prompt: Attack Techniques For Language Models How much the field cites it — very heavily cited in the last 12 months 475 in the last 12 months · 1055 total published 2022 checked 2026-09-04 click for Semantic Scholar PAL: Program-aided Language Models paper · Luyu Gao et al.
2022 2026-09-02 This source: PAL: Program-aided Language Models How much the field cites it — very heavily cited in the last 12 months 268 in the last 12 months · 824 total published 2022 checked 2026-09-04 Constitutional AI: Harmlessness from AI Feedback paper · Yuntao Bai et al.
2022 2026-09-02 This source: Constitutional AI: Harmlessness from AI Feedback How much the field cites it — very heavily cited in the last 12 months 1000+ in the last 12 months · 3617 total published 2022 checked 2026-09-04 count capped at 1000 by the fetch click for Semantic Scholar Toolformer: Language Models Can Teach Themselves to Use Tools paper · Timo Schick et al.
2023 2026-09-02 This source: Toolformer: Language Models Can Teach Themselves to Use Tools How much the field cites it — very heavily cited in the last 12 months 1000+ in the last 12 months · 5422 total published 2023 checked 2026-09-04 count capped at 1000 by the fetch click for Semantic Scholar Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection paper · Kai Greshake et al.
2023 2026-09-02 This source: Not what you've signed up for: Compromising Real-World LLM-Integrated … How much the field cites it — very heavily cited in the last 12 months 1000+ in the last 12 months · 1870 total published 2023 checked 2026-09-04 count capped at 1000 by the fetch Reflexion: Language Agents with Verbal Reinforcement Learning paper · Noah Shinn et al.
2023 2026-09-02 This source: Reflexion: Language Agents with Verbal Reinforcement Learning How much the field cites it — very heavily cited in the last 12 months 1000+ in the last 12 months · 5075 total published 2023 checked 2026-09-04 count capped at 1000 by the fetch Self-Refine: Iterative Refinement with Self-Feedback paper · Aman Madaan et al.
2023 2026-09-02 This source: Self-Refine: Iterative Refinement with Self-Feedback How much the field cites it — very heavily cited in the last 12 months 1000+ in the last 12 months · 4530 total published 2023 checked 2026-09-04 count capped at 1000 by the fetch Generative Agents: Interactive Simulacra of Human Behavior paper · Joon Sung Park et al.
2023 2026-09-02 This source: Generative Agents: Interactive Simulacra of Human Behavior How much the field cites it — very heavily cited in the last 12 months 1000+ in the last 12 months · 5387 total published 2023 checked 2026-09-04 count capped at 1000 by the fetch click for Semantic Scholar Entity Tracking in Language Models paper · Najoung Kim et al.
2023 2026-09-02 This source: Entity Tracking in Language Models How much the field cites it — steadily cited in the last 12 months 14 in the last 12 months · 43 total published 2023 checked 2026-09-04 click for Semantic Scholar Adaptive Chameleon or Stubborn Sloth: Revealing the Behavior of Large Language Models in Knowledge Conflicts paper · Jian Xie et al.
2023 2026-09-02 This source: Adaptive Chameleon or Stubborn Sloth: Revealing the Behavior of Large … How much the field cites it — heavily cited in the last 12 months 148 in the last 12 months · 382 total published 2023 checked 2026-09-04 FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation paper · Sewon Min et al.
2023 2026-09-02 This source: FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long… How much the field cites it — very heavily cited in the last 12 months 697 in the last 12 months · 1643 total published 2023 checked 2026-09-04 click for Semantic Scholar Gorilla: Large Language Model Connected with Massive APIs paper · Shishir G. Patil et al.
2023 2026-09-02 This source: Gorilla: Large Language Model Connected with Massive APIs How much the field cites it — very heavily cited in the last 12 months 805 in the last 12 months · 1585 total published 2023 checked 2026-09-04 Large Language Models are not Fair Evaluators paper · Peiyi Wang et al.
2023 2026-09-02 This source: Large Language Models are not Fair Evaluators How much the field cites it — very heavily cited in the last 12 months 506 in the last 12 months · 1242 total published 2023 checked 2026-09-04 Faith and Fate: Limits of Transformers on Compositionality paper · Nouha Dziri et al.
2023 2026-09-02 This source: Faith and Fate: Limits of Transformers on Compositionality How much the field cites it — very heavily cited in the last 12 months 229 in the last 12 months · 690 total published 2023 checked 2026-09-04 Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena paper · Lianmin Zheng et al.
2023 2026-09-02 This source: Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena How much the field cites it — very heavily cited in the last 12 months 1000+ in the last 12 months · 10936 total published 2023 checked 2026-09-04 count capped at 1000 by the fetch click for Semantic Scholar Lost in the Middle: How Language Models Use Long Contexts paper · Nelson F. Liu et al.
2023 2026-09-02 This source: Lost in the Middle: How Language Models Use Long Contexts How much the field cites it — very heavily cited in the last 12 months 1000+ in the last 12 months · 4887 total published 2023 checked 2026-09-04 count capped at 1000 by the fetch WebArena: A Realistic Web Environment for Building Autonomous Agents paper · Shuyan Zhou et al.
2023 2026-09-02 This source: WebArena: A Realistic Web Environment for Building Autonomous Agents How much the field cites it — very heavily cited in the last 12 months 1000+ in the last 12 months · 1931 total published 2023 checked 2026-09-04 count capped at 1000 by the fetch ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs paper · Yujia Qin et al.
2023 2026-09-02 This source: ToolLLM: Facilitating Large Language Models to Master 16000+ Real-worl… How much the field cites it — very heavily cited in the last 12 months 1000+ in the last 12 months · 2160 total published 2023 checked 2026-09-04 count capped at 1000 by the fetch AgentBench: Evaluating LLMs as Agents paper · Xiao Liu et al.
2023 2026-09-02 This source: AgentBench: Evaluating LLMs as Agents How much the field cites it — very heavily cited in the last 12 months 797 in the last 12 months · 1243 total published 2023 checked 2026-09-04 Simple synthetic data reduces sycophancy in large language models paper · Jerry Wei et al.
2023 2026-09-02 This source: Simple synthetic data reduces sycophancy in large language models How much the field cites it — heavily cited in the last 12 months 92 in the last 12 months · 181 total published 2023 checked 2026-09-04 Recursively Summarizing Enables Long-Term Dialogue Memory in Large Language Models paper · Qingyue Wang et al.
2023 2026-09-02 This source: Recursively Summarizing Enables Long-Term Dialogue Memory in Large Lan… How much the field cites it — heavily cited in the last 12 months 51 in the last 12 months · 93 total published 2023 checked 2026-09-04 The Reversal Curse: LLMs trained on "A is B" fail to learn "B is A" paper · Lukas Berglund et al.
2023 2026-09-02 This source: The Reversal Curse: LLMs trained on "A is B" fail to learn "B is A" How much the field cites it — heavily cited in the last 12 months 174 in the last 12 months · 530 total published 2023 checked 2026-09-04 Large Language Models Cannot Self-Correct Reasoning Yet paper · Jie Huang et al.
2023 2026-09-02 This source: Large Language Models Cannot Self-Correct Reasoning Yet How much the field cites it — very heavily cited in the last 12 months 503 in the last 12 months · 1164 total published 2023 checked 2026-09-04 SWE-bench: Can Language Models Resolve Real-World GitHub Issues? paper · Carlos E. Jimenez et al.
2023 2026-09-02 This source: SWE-bench: Can Language Models Resolve Real-World GitHub Issues? How much the field cites it — very heavily cited in the last 12 months 1000+ in the last 12 months · 3594 total published 2023 checked 2026-09-04 count capped at 1000 by the fetch no claims yet MemGPT: Towards LLMs as Operating Systems paper · Charles Packer et al.
2023 2026-09-02 This source: MemGPT: Towards LLMs as Operating Systems How much the field cites it — very heavily cited in the last 12 months 984 in the last 12 months · 1246 total published 2023 checked 2026-09-04 click for Semantic Scholar Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection paper · Akari Asai et al.
2023 2026-09-02 This source: Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Re… How much the field cites it — very heavily cited in the last 12 months 1000+ in the last 12 months · 2517 total published 2023 checked 2026-09-04 count capped at 1000 by the fetch Towards Understanding Sycophancy in Language Models paper · Mrinank Sharma et al.
2023 2026-09-02 This source: Towards Understanding Sycophancy in Language Models How much the field cites it — very heavily cited in the last 12 months 846 in the last 12 months · 1274 total published 2023 checked 2026-09-04 click for Semantic Scholar A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions paper · Lei Huang et al.
2023 2026-09-02 This source: A Survey on Hallucination in Large Language Models: Principles, Taxono… How much the field cites it — very heavily cited in the last 12 months 1000+ in the last 12 months · 3664 total published 2023 checked 2026-09-04 count capped at 1000 by the fetch Instruction-Following Evaluation for Large Language Models paper · Jeffrey Zhou et al.
2023 2026-09-02 This source: Instruction-Following Evaluation for Large Language Models How much the field cites it — very heavily cited in the last 12 months 625 in the last 12 months · 1081 total published 2023 checked 2026-09-04 Purple Llama CyberSecEval: A Secure Coding Benchmark for Language Models paper · Manish Bhatt et al.
2023 2026-09-02 This source: Purple Llama CyberSecEval: A Secure Coding Benchmark for Language Mode… How much the field cites it — heavily cited in the last 12 months 73 in the last 12 months · 180 total published 2023 checked 2026-09-04 click for Semantic Scholar StruQ: Defending Against Prompt Injection with Structured Queries paper · Sizhe Chen et al.
2024 2026-09-02 This source: StruQ: Defending Against Prompt Injection with Structured Queries How much the field cites it — very heavily cited in the last 12 months 243 in the last 12 months · 394 total published 2024 checked 2026-09-04 Same Task, More Tokens: the Impact of Input Length on the Reasoning Performance of Large Language Models paper · Mosh Levy et al.
2024 2026-09-02 This source: Same Task, More Tokens: the Impact of Input Length on the Reasoning Pe… How much the field cites it — heavily cited in the last 12 months 104 in the last 12 months · 238 total published 2024 checked 2026-09-04 click for Semantic Scholar Tokenization counts: the impact of tokenization on arithmetic in frontier LLMs paper · Aaditya K. Singh et al.
2024 2026-09-02 This source: Tokenization counts: the impact of tokenization on arithmetic in front… How much the field cites it — steadily cited in the last 12 months 44 in the last 12 months · 126 total published 2024 checked 2026-09-04 click for Semantic Scholar Reverse Training to Nurse the Reversal Curse paper · Olga Golovneva et al.
2024 2026-09-02 This source: Reverse Training to Nurse the Reversal Curse How much the field cites it — steadily cited in the last 12 months 15 in the last 12 months · 60 total published 2024 checked 2026-09-04 Long-form factuality in large language models paper · Jerry Wei et al.
2024 2026-09-02 This source: Long-form factuality in large language models How much the field cites it — heavily cited in the last 12 months 75 in the last 12 months · 167 total published 2024 checked 2026-09-04 RULER: What's the Real Context Size of Your Long-Context Language Models? paper · Cheng-Ping Hsieh et al.
2024 2026-09-02 This source: RULER: What's the Real Context Size of Your Long-Context Language Mode… How much the field cites it — very heavily cited in the last 12 months 759 in the last 12 months · 1243 total published 2024 checked 2026-09-04 The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions paper · Eric Wallace et al.
2024 2026-09-02 This source: The Instruction Hierarchy: Training LLMs to Prioritize Privileged Inst… How much the field cites it — very heavily cited in the last 12 months 285 in the last 12 months · 486 total published 2024 checked 2026-09-04 click for Semantic Scholar Transformers Can Do Arithmetic with the Right Embeddings paper · Sean McLeish et al.
2024 2026-09-02 This source: Transformers Can Do Arithmetic with the Right Embeddings How much the field cites it — steadily cited in the last 12 months 36 in the last 12 months · 91 total published 2024 checked 2026-09-04 click for Semantic Scholar Evaluating the World Model Implicit in a Generative Model paper · Keyon Vafa et al.
2024 2026-09-02 This source: Evaluating the World Model Implicit in a Generative Model How much the field cites it — heavily cited in the last 12 months 75 in the last 12 months · 144 total published 2024 checked 2026-09-04 Sycophancy to Subterfuge: Investigating Reward-Tampering in Large Language Models paper · Carson Denison et al.
2024 2026-09-02 This source: Sycophancy to Subterfuge: Investigating Reward-Tampering in Large Lang… How much the field cites it — heavily cited in the last 12 months 89 in the last 12 months · 158 total published 2024 checked 2026-09-04 click for Semantic Scholar We Have a Package for You! A Comprehensive Analysis of Package Hallucinations by Code Generating LLMs paper · Joseph Spracklen et al.
2024 2026-09-02 This source: We Have a Package for You! A Comprehensive Analysis of Package Halluci… How much the field cites it — heavily cited in the last 12 months 80 in the last 12 months · 106 total published 2024 checked 2026-09-04 τ-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains paper · Shunyu Yao et al.
2024 2026-09-02 This source: τ-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Dom… How much the field cites it — very heavily cited in the last 12 months 889 in the last 12 months · 1075 total published 2024 checked 2026-09-04 AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents paper · Maksym Andriushchenko et al.
2024 2026-09-02 This source: AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents How much the field cites it — very heavily cited in the last 12 months 270 in the last 12 months · 376 total published 2024 checked 2026-09-04 LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory paper · Di Wu et al.
2024 2026-09-02 This source: LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Mem… How much the field cites it — very heavily cited in the last 12 months 517 in the last 12 months · 588 total published 2024 checked 2026-09-04 Frontier Models are Capable of In-context Scheming paper · Alexander Meinke et al.
2024 2026-09-02 This source: Frontier Models are Capable of In-context Scheming How much the field cites it — heavily cited in the last 12 months 189 in the last 12 months · 288 total published 2024 checked 2026-09-04 click for Semantic Scholar Agent-SafetyBench: Evaluating the Safety of LLM Agents paper · Zhexin Zhang et al.
2024 2026-09-02 This source: Agent-SafetyBench: Evaluating the Safety of LLM Agents How much the field cites it — heavily cited in the last 12 months 194 in the last 12 months · 256 total published 2024 checked 2026-09-04