Claims

Axis of disagreement(a guess, not verified): Whether the load-bearing mechanism is individual standing (reputation from outcomes) or structural diversity of agreement (bridging). Both could hold in different regimes: bridging needs many raters per item, which a specialist catalog will not have; reputation needs a resolution rule, which a catalog of falsifiable claims supplies.

• ↑ supportsOutcome-based reputation as the incentive for a human-and-agent knowledge commons
• ↑ supportsGrokipedia is dead. I'd like to rescue it, starting with scientific data
• ↑ supportsResearchers found dopamine neurons inside LLMs
• ↑ supportsConsequence of a "publish or perish" academic mindset rather than anything serious
• ↓ contestsBirdwatch: Crowd Wisdom and Bridging Algorithms can Inform Understanding and Reduce the Spread of Misinformation

Axis of disagreement(a guess, not verified): Task horizon, and how the aggregate is taken. The supporting benchmark scores whole interactive episodes, where open models trailed in 2023; the contesting one scores a ladder whose lower tiers are short structured calls by construction, on 2026 open weights, and reports an aggregate across all tiers. Both agree open models lag on long-horizon planning, so the disagreement may be about what "agent work" averages over, and about two and a half years of open-weight progress, rather than about a fact.

• ↑ supportsAgentBench: Evaluating LLMs as AgentsThis source: AgentBench: Evaluating LLMs as AgentsHow much the field cites it — very heavily cited in the last 12 months797 in the last 12 months · 1243 totalpublished 2023checked 2026-09-04
• ↓ contestsAgentFloor: How Far Up the tool use Ladder Can Small Open-Weight Models Go?

Axis of disagreement(a guess, not verified): Probably the outcome variable, and possibly the file's origin. The study measures success on tasks the agent has never seen, in repositories where the file was written generically or generated by the agent; the practitioner claim is about a file that accumulates the exact failures one team's agent made in one codebase, measured by whether those failures recur. A file of non-obvious project deviations might do the second job while adding nothing to the first — the study's own developer-written condition trends that way (+2.4%, not significant). If that is right, the technique's value is in what goes in the file, not in having one. Not tested against each other.

• ↑ supportsEvaluating AGENTS.md: Are Repository-Level Context Files Helpful for Coding Agents?
• ↓ contestsMy AI Adoption Journey – Mitchell Hashimoto
• ↓ contestsHarness Engineering — Agent = Model + Harness: The 6-Layer Production Playbook

Axis of disagreement(a guess, not verified): Likely how rigorously the baseline (no-revision) condition was set up and evaluated, and possibly task family — open-ended generation tasks (where "better" is fuzzier and easier to nudge with a second pass) vs. the more checkable reasoning benchmarks in the contesting paper. I haven't reconciled the two papers' exact experimental setups myself.

• ↑ supportsSelf-Refine: Iterative Refinement with Self-FeedbackThis source: Self-Refine: Iterative Refinement with Self-FeedbackHow much the field cites it — very heavily cited in the last 12 months1000+ in the last 12 months · 4530 totalpublished 2023checked 2026-09-04count capped at 1000 by the fetch
• ↓ contestsLarge Language Models Cannot Self-Correct Reasoning YetThis source: Large Language Models Cannot Self-Correct Reasoning YetHow much the field cites it — very heavily cited in the last 12 months503 in the last 12 months · 1164 totalpublished 2023checked 2026-09-04

Axis of disagreement(a guess, not verified): Probably task family and how "improvement" was measured. The contesting result is strongest on open-ended generation, where better is a fuzzy judgment a second pass can nudge; the supporting results are on checkable tasks with a pass/fail signal. A secondary possibility is baseline setup — whether the no-revision comparison got the same inference budget. I have not reconciled the experimental setups myself.

• ↑ supportsReflexion: Language Agents with Verbal Reinforcement LearningThis source: Reflexion: Language Agents with Verbal Reinforcement LearningHow much the field cites it — very heavily cited in the last 12 months1000+ in the last 12 months · 5075 totalpublished 2023checked 2026-09-04count capped at 1000 by the fetch
• ↑ supportsLarge Language Models Cannot Self-Correct Reasoning YetThis source: Large Language Models Cannot Self-Correct Reasoning YetHow much the field cites it — very heavily cited in the last 12 months503 in the last 12 months · 1164 totalpublished 2023checked 2026-09-04
• ↓ contestsSelf-Refine: Iterative Refinement with Self-FeedbackThis source: Self-Refine: Iterative Refinement with Self-FeedbackHow much the field cites it — very heavily cited in the last 12 months1000+ in the last 12 months · 4530 totalpublished 2023checked 2026-09-04count capped at 1000 by the fetch

Axis of disagreement(a guess, not verified): Two axes now, because there are three positions. The first is what the other passages are. The supporting result places one relevant passage among distractors, where moving it out of the middle recovers accuracy that position was costing. The 2026 conflict result places several mutually incompatible passages of equal legitimacy, where position is not degrading access to a known answer but deciding which answer wins — and reordering only moves which passage occupies the winning slot. If that is right, both hold, and ordering is a remedy for distraction rather than for conflict. The second is model generation, and it cuts across the first. Anthropic says the end-of-context bias it used to prompt around is largely gone in the Claude 5 generation. So the effect may be real, real still under conflict, and being trained away for ordinary retrieval — three claims that can all hold at once about different models at different times. This is exactly what the mechanism-versus-observation split is for, and it is an argument that this claim is closer to observation than it is currently filed. I have not tested any of the three setups against each other.

• ↑ supportsLost in the Middle: How Language Models Use Long ContextsThis source: Lost in the Middle: How Language Models Use Long ContextsHow much the field cites it — very heavily cited in the last 12 months1000+ in the last 12 months · 4887 totalpublished 2023checked 2026-09-04count capped at 1000 by the fetch
• ↓ contestsLarge Language Models in Resolving Contextual Knowledge Conflicts
• ↓ contestsThe new rules of context engineering for Claude 5 generation models

Axis of disagreement(a guess, not verified): Probably what the prompting is being asked to do. The supporting results have the model perform the arithmetic across steps; the contesting result has prompting re-represent the operands (comma separation, converting between tokenizations) so the model's existing arithmetic circuitry engages. Those are different interventions wearing the same name. I have not tested whether the recovery survives on operand sizes as large as the compositionality work uses.

• ↑ supportsPAL: Program-aided Language ModelsThis source: PAL: Program-aided Language ModelsHow much the field cites it — very heavily cited in the last 12 months268 in the last 12 months · 824 totalpublished 2022checked 2026-09-04
• ↑ supportsFaith and Fate: Limits of Transformers on CompositionalityThis source: Faith and Fate: Limits of Transformers on CompositionalityHow much the field cites it — very heavily cited in the last 12 months229 in the last 12 months · 690 totalpublished 2023checked 2026-09-04
• ↓ contestsTokenization counts: the impact of tokenization on arithmetic in frontier LLMsThis source: Tokenization counts: the impact of tokenization on arithmetic in front…How much the field cites it — steadily cited in the last 12 months44 in the last 12 months · 126 totalpublished 2024checked 2026-09-04click for Semantic Scholar

• ↑ supportsSingProbe Technical Report

• ↑ supportsHarness Engineering — Agent = Model + Harness: The 6-Layer Production Playbook
• ↑ supportsMy AI Adoption Journey – Mitchell Hashimoto

• ↑ supportsHarness-Bench: Measuring Harness Effects across Models in Realistic Agent Workflows
• ↑ supportsHAL GAIA Leaderboard (Holistic Agent Leaderboard, Princeton)
• ↑ supportsHarness Engineering — Agent = Model + Harness: The 6-Layer Production Playbook
• ↑ supportsAgentic Harness Engineering: The Operating System for Machine Intelligence
• ↑ supportsImproving Deep Agents with harness engineering
• ↑ supportsI Improved 15 LLMs at Coding in One Afternoon. Only the Harness Changed.

• ↑ supportsSeed-Prover 1.5: Mastering Undergraduate-Level Theorem Proving via Learning from Experience

• ↑ supportsThe Calls are Coming from Inside the Model: Investigating Probe-based Detection of Tool-Calling Errors in LLMs

• ↑ supportsThe Calls are Coming from Inside the Model: Investigating Probe-based Detection of Tool-Calling Errors in LLMs

• ↑ supportsDomain-Specific Jargon in Large Language Models: A Comparative Analysis between General-Purpose and Specialist Models

• ↑ supportsGenerative Agents: Interactive Simulacra of Human BehaviorThis source: Generative Agents: Interactive Simulacra of Human BehaviorHow much the field cites it — very heavily cited in the last 12 months1000+ in the last 12 months · 5387 totalpublished 2023checked 2026-09-04count capped at 1000 by the fetchclick for Semantic Scholar

• ↑ supportsHow Identity and Opinion Shape Political Sycophancy in LLMs

• ↑ supportsHow Identity and Opinion Shape Political Sycophancy in LLMs

• ↑ supportsA light-touch AI literacy intervention helps protect against AI political persuasion

• ↑ supportsApproaching Human-Level Forecasting with Language ModelsThis source: Approaching Human-Level Forecasting with Language ModelsHow much the field cites it — heavily cited in the last 12 months76 in the last 12 months · 125 totalpublished 2024checked 2026-09-04click for Semantic Scholar

• ↑ supportsRecursively Summarizing Enables Long-Term Dialogue Memory in Large Language ModelsThis source: Recursively Summarizing Enables Long-Term Dialogue Memory in Large Lan…How much the field cites it — heavily cited in the last 12 months51 in the last 12 months · 93 totalpublished 2023checked 2026-09-04
• ↑ supportsLongMemEval: Benchmarking Chat Assistants on Long-Term Interactive MemoryThis source: LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Mem…How much the field cites it — very heavily cited in the last 12 months517 in the last 12 months · 588 totalpublished 2024checked 2026-09-04

• ↑ supportsRevisiting Ripple Effects in Knowledge Editing through Pressure-Aware Joint Neighborhood Optimization

• ↑ supportsMemGPT: Towards LLMs as Operating SystemsThis source: MemGPT: Towards LLMs as Operating SystemsHow much the field cites it — very heavily cited in the last 12 months984 in the last 12 months · 1246 totalpublished 2023checked 2026-09-04click for Semantic Scholar

• ↑ supportsLarge Language Models Struggle to Learn Long-Tail KnowledgeThis source: Large Language Models Struggle to Learn Long-Tail KnowledgeHow much the field cites it — very heavily cited in the last 12 months203 in the last 12 months · 730 totalpublished 2022checked 2026-09-04

• ↑ supportsDo Large Language Models Know What They Don't Know II? A Fully Behavioral, Non-Cognitive Measure of Epistemic Honesty

• ↑ supportsUnderstanding Syllogistic Reasoning in LLMs from Formal and Natural Language Perspectives

• ↑ supportsMeasuring Activation Control in Large Language Models

• ↑ supportsWhen Linguistic and Internal Confidence Diverge in Large Language Models

• ↑ supportsThe Last AI Built by Humans: Toward Genuine Recursive Self-Improvement

• ↑ supportsSingle-Agent Scaling Fails Multi-Agent Intelligence: Towards Foundation Models with Native Multi-Agent Intelligence

• ↑ supportsLLM-based Agents for Forecasting and Prediction: Methods, Training, Evaluation, and Applications

• ↑ supportsAgent-SafetyBench: Evaluating the Safety of LLM AgentsThis source: Agent-SafetyBench: Evaluating the Safety of LLM AgentsHow much the field cites it — heavily cited in the last 12 months194 in the last 12 months · 256 totalpublished 2024checked 2026-09-04

• ↑ supportsWe Have a Package for You! A Comprehensive Analysis of Package Hallucinations by Code Generating LLMsThis 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 months80 in the last 12 months · 106 totalpublished 2024checked 2026-09-04

• ↑ supportsAn Empirical Evaluation of Prompt Injection Vulnerabilities in Large Language Models Across Multilingual and Obfuscated Attack Scenarios

• ↑ supportsThinking Inertia: LLMs Keep Thinking When Told Not To

• ↑ supportsDo Methods to Jailbreak and Defend LLMs Generalize Across Languages?

• ↑ supportsRepoGraph: Enhancing AI Software Engineering with Repository-level Code Graph

• ↑ supportsSame Task, More Tokens: the Impact of Input Length on the Reasoning Performance of Large Language ModelsThis 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 months104 in the last 12 months · 238 totalpublished 2024checked 2026-09-04click for Semantic Scholar

• ↑ supportsThe Universe of Universes: Benefit Yield Functions, Implosion Thresholds, and Infrastructure-Aware Optimization in Multi-LLM Systems

• ↑ supportsAgentHarm: A Benchmark for Measuring Harmfulness of LLM AgentsThis source: AgentHarm: A Benchmark for Measuring Harmfulness of LLM AgentsHow much the field cites it — very heavily cited in the last 12 months270 in the last 12 months · 376 totalpublished 2024checked 2026-09-04

• ↑ supports"TODO: Fix the Mess Gemini Created": Towards Understanding GenAI-Induced Self-Admitted Technical Debt

• ↑ supportsMitigating LLM Hallucinations via Conformal Abstention

• ↑ supportsTokenization counts: the impact of tokenization on arithmetic in frontier LLMsThis source: Tokenization counts: the impact of tokenization on arithmetic in front…How much the field cites it — steadily cited in the last 12 months44 in the last 12 months · 126 totalpublished 2024checked 2026-09-04click for Semantic Scholar

• ↑ supportsLarge Language Models are not Fair EvaluatorsThis source: Large Language Models are not Fair EvaluatorsHow much the field cites it — very heavily cited in the last 12 months506 in the last 12 months · 1242 totalpublished 2023checked 2026-09-04
• ↑ supportsJudging LLM-as-a-Judge with MT-Bench and Chatbot ArenaThis source: Judging LLM-as-a-Judge with MT-Bench and Chatbot ArenaHow much the field cites it — very heavily cited in the last 12 months1000+ in the last 12 months · 10936 totalpublished 2023checked 2026-09-04count capped at 1000 by the fetchclick for Semantic Scholar

• ↑ supportsTrustworthy Agentic AI: Failure Modes, Mitigation Strategies, and a Lifecycle Framework for Autonomous LLM Systems

• ↑ supportsMedProbeBench: Systematic Benchmarking at Deep Evidence Integration for Expert-level Medical Guideline

• ↑ supportsKnowing the Facts but Choosing the Shortcut: Understanding How Large Language Models Compare Entities

• ↑ supportsTraining-Free Cultural Alignment of Large Language Models via Persona Disagreement

• ↑ supportsAI-Generated Smells: An Analysis of Code and Architecture in LLM and Agent-Driven Development

• ↑ supportsAutoformalizer with Tool Feedback

• ↑ supportsAI-Generated Code Is Not Reproducible (Yet): An Empirical Study of Dependency Gaps in LLM-Based Coding Agents
• ↑ supportsWe Have a Package for You! A Comprehensive Analysis of Package Hallucinations by Code Generating LLMsThis 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 months80 in the last 12 months · 106 totalpublished 2024checked 2026-09-04

• ↑ supportsTowards Understanding Sycophancy in Language ModelsThis source: Towards Understanding Sycophancy in Language ModelsHow much the field cites it — very heavily cited in the last 12 months846 in the last 12 months · 1274 totalpublished 2023checked 2026-09-04click for Semantic Scholar

• ↑ supportsLongMemEval: Benchmarking Chat Assistants on Long-Term Interactive MemoryThis source: LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Mem…How much the field cites it — very heavily cited in the last 12 months517 in the last 12 months · 588 totalpublished 2024checked 2026-09-04

• ↑ supportsOrcaLoca: An LLM Agent Framework for Software Issue Localization

• ↑ supportsClaim-Level Confidence Calibration for Reliable Decision Making with Large Language Models

• ↑ supportsTICKing All the Boxes: Generated Checklists Improve LLM Evaluation and GenerationThis source: TICKing All the Boxes: Generated Checklists Improve LLM Evaluation and…How much the field cites it — steadily cited in the last 12 months33 in the last 12 months · 61 totalpublished 2024checked 2026-09-04click for Semantic Scholar

• ↑ supportsLong-form factuality in large language modelsThis source: Long-form factuality in large language modelsHow much the field cites it — heavily cited in the last 12 months75 in the last 12 months · 167 totalpublished 2024checked 2026-09-04

• ↑ supportsNot what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt InjectionThis 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 months1000+ in the last 12 months · 1870 totalpublished 2023checked 2026-09-04count capped at 1000 by the fetch

• ↑ supportsAn Empirical Evaluation of Prompt Injection Vulnerabilities in Large Language Models Across Multilingual and Obfuscated Attack Scenarios

• ↑ supportsThinking Inertia: LLMs Keep Thinking When Told Not To

• ↑ supportsA Metamorphic Testing Approach to Diagnosing Memorization in LLM-Based Program Repair

• ↑ supportsModularRSI: Modular and Generalizable Recursive Harness Self-Improvement
• ↑ supportsImpressive paper on building recursive self-improving agent harnesses

• ↑ supportsNumeracy in Large Language Models: Fundamental Limitations and Paths to Improvement

• ↑ supportsImpact of Pretraining Term Frequencies on Few-Shot ReasoningThis source: Impact of Pretraining Term Frequencies on Few-Shot ReasoningHow much the field cites it — steadily cited in the last 12 months15 in the last 12 months · 191 totalpublished 2022checked 2026-09-04click for Semantic Scholar

• ↑ supportsHEJ-Robust: A Robustness Benchmark for LLM-Based Automated Program Repair

• ↑ supportsVISA: Agentic Self-Evolving Data Synthesis for Multimodal Instruction Following

• ↑ supportsAligned but Flattened: Analyzing the Trade-off between Cultural Alignment and Diversity in LLMs

• ↑ supportsToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIsThis source: ToolLLM: Facilitating Large Language Models to Master 16000+ Real-worl…How much the field cites it — very heavily cited in the last 12 months1000+ in the last 12 months · 2160 totalpublished 2023checked 2026-09-04count capped at 1000 by the fetch

• ↑ supportsSimple synthetic data reduces sycophancy in large language modelsThis source: Simple synthetic data reduces sycophancy in large language modelsHow much the field cites it — heavily cited in the last 12 months92 in the last 12 months · 181 totalpublished 2023checked 2026-09-04

• ↑ supportsTowards Understanding Sycophancy in Language ModelsThis source: Towards Understanding Sycophancy in Language ModelsHow much the field cites it — very heavily cited in the last 12 months846 in the last 12 months · 1274 totalpublished 2023checked 2026-09-04click for Semantic Scholar

• ↑ supportsGUT: Quantifying and Optimizing the Reasoning Uncertainty of LLMs via Graph Complexity

• ↑ supportsAgenticRag-R1: Agentic Reinforcement Learning with Stack Memory for Multi-Step Reasoning, Retrieval and Memorizing

• ↑ supportsCPR for LLMs: Critical-Point Routing against Catastrophic Forgetting in Domain Adaptation

• ↑ supportsCOMET: Contrastive Motion-Enhanced Temporal Reasoning for Video Multimodal Large Language Models

• ↑ supportsCOMET: Contrastive Motion-Enhanced Temporal Reasoning for Video Multimodal Large Language Models

• ↑ supportsEnhancing Localized Reasoning for Long Video Understanding via Efficient Segment-to-Video Supervision

• ↑ supportsSPADE: Self-Play in Adaptive Synthetic Executable Environments

• ↑ supportsMidTool: Mid-training Data Synthesis for Agentic Tool Use

• ↑ supportsVideo-OPSD: Exploiting Privileged Visual Evidence for On-Policy Self-Distillation in Video Large Language Models

• ↑ supportsSemantic-Spatial Agreement Verification for Mitigating Object Hallucination in Multimodal Large Language Models

• ↑ supportsEvaluation of MLLM-Agnostic Plug-and-Play Keyframe Selection Methods for Long Video Understanding

• ↑ supportsCredal Large Language Models for Semantic Commitment under Uncertainty

• ↑ supportsVideoScout: Learning Agentic Active Exploration with Adaptive Reasoning Pacing for Long Video Understanding

• ↑ supportsSemantic Reasoning Denoising: Correcting Language Model Reasoning with Semantic Operators

• ↑ supportsSemantic Reasoning Denoising: Correcting Language Model Reasoning with Semantic Operators

• ↑ supportsSAVOR: Self-Aware Visual Grounding via Confidence-Calibrated Reinforcement Learning for Multimodal Hallucination Mitigation

• ↑ supportsUniRRM: Unified Reasoning Reward Models Across Languages and Evaluation Paradigms

• ↑ supportsSpecCoder: Specification-Aware Code Generation with Curriculum Dual-Task Reinforcement Learning

• ↑ supportsDistillCache: KL-Guided Adaptive KV-Cache Eviction for Memory-Efficient LLM Inference

• ↑ supportsLLM-Based FORM Code Generation with Verification-Driven Fine-Tuning

• ↑ supportsRoute-Align-Verify for Functional Correctness in Code Generation

• ↑ supportsTraining-Free Inference-Time Self-Reflection and Cost-Bounded Early Stopping for Large Language Models

• ↑ supportsHypoForge: A Self-Improving Multi-Agent Framework for Automated Hypothesis Generation and Testing via Scientific Skill Learning

• ↑ supportsMedClaw: Heuristic Agent Harness for Long-Horizon Surgical Video Reasoning

• ↑ supportsGRIP: Granular Reward-Guided Parameter Interpolation for Efficient Reasoning

• ↑ supportsExperience Funnel: A State-Policy Alternating Loop for Self-Evolving Agents

• ↑ supportsSFT or RL for Tool-Calling Agents? A Controlled Study Across Data, Method, and Scale

• ↑ supportsPRO-Step: Step-level Process Reward Optimization for Retrieval-Augmented Generation

• ↑ supportsActionable Hallucination Detection: Translating Latent Uncertainty into Agentic Critique

• ↑ supportsEvoOntology: A Self-Evolving Ontology Layer for Data Agents

• ↑ supportsARM: Attention with Routed-Memory for Learnable Sparse Control

• ↑ supportsSwarmBench: Can Large Language Models Act as Agent Swarm Orchestrators?

• ↑ supportsEnhancing Automated Unit Test Generation for NLP Libraries Using Large Language Models

• ↑ supportsSWE Refactor Bench: Can Coding Agents Complete a Long-Horizon, Whole-Repository Stack Migration?

• ↑ supportsHSRM: Hidden-State Reward Models for Test-Time Verification

• ↑ supportsUHP Detection: LVLMs have their Unique Hallucination Pattern in the Consistency Space

• ↑ supportsFrom Tokens to Semantics: Leveraging Complementary Signals for Hallucination Detection in Black-Box LLMs

• ↑ supportsA Self-Evolving Multi-Agent Framework Defense against LLM Jailbreak Attacks

• ↑ supportsWhat Do CAE Simulation Agents Really Need Beyond a Generic Harness?

• ↑ supportsGRACE: Graph-Grounded Reflective Agent Copilot Engine for Expert-in-the-Loop Knowledge Expansion

• ↑ supportsWhen Do Supervised UQ Ensembles Improve LLM Hallucination Detection? A Robustness Study

• ↑ supportsClaim-Level Confidence Calibration for Reliable Decision Making with Large Language Models

• ↑ supportsKeep Evaluation Fair: Detecting Data Leakage in Code Generation Benchmarks via Membership Inference Attacks

• ↑ supportsCoding Agents with an Obstacle-Aware Harness for Safe Robot Manipulation

• ↑ supportsWrapper Induction: Efficiency and Expressiveness

• ↑ supportsSIR: Self-improving Red-teaming for Compute Use Agents

• ↑ supportsAutoViewMem: Self-Configuring Orthogonal Views for Conversational Long-Term Memory

• ↑ supportsDSEffi-Bench: Demystifying Large Language Models' Capability in Efficient Data Science Code Generation

• ↑ supportsStageGuard: Learning Stage Transitions for Long-Horizon Robot Tasks via Agentic Distillation

• ↑ supportsOrigin Is All You Need: Provenance-Aware Transformers for Structural Trust-Boundary Separation

• ↑ supportsMulti-Agent Forensic Reasoning for Generalizable Deepfake Video Detection

• ↑ supportsError Detection for PET/CT Radiology Reports: Domain-Specific vs Large Language Models

• ↑ supportsSpanCalib-VLM: Calibrated Hallucination Span Detection in Vision-Language Models

• ↑ supportsVisER: Visual Evidence and Reliance for Object Hallucination Detection in LVLMs

• ↑ supportsCapek 0.5: An Execution-Centric Vision-Language Model for Embodied Intelligence

• ↑ supportsDomain-Specific Hallucination Detection in Large Language Models

• ↑ supportsCUSP: Decomposable Collective Uncertainty for Multi-Agent Multimodal Reasoning

• ↑ supportsTwin Worlds: Equivariance-Based Abstention for Evidence-Grounded Reasoning

• ↑ supportsAutomatic XPath generation agents for vertical websites by LLMs

• ↑ supportsWhen the Wrong Key Wins: Understanding and Detecting Hallucinations in LLMs

• ↑ supportsAI Slop and Hallucinations in Vulnerability Assessment: A Survey on Reasoning Failures and Trustworthy Mitigation

• ↑ supportsFrontiers in FinTech: Multimodal Foundation Models for Financial Reporting and Decision Science

• ↑ supportsAGM: Achievement-Grounded Memory for Closed-Loop Agents with Frozen VLA Policies

• ↑ supportsBeam Search, Self-Consistency, and the Limits of Inference-Time Scaling for Grammar-Constrained Text-to-SQL in Small Language Models

• ↑ supportsAesCanvas: A Large-Scale Dataset and Benchmark for Aesthetic Critique and Contextual Suitability

• ↑ supportsAn Experimental Evaluation of Multimodal Prompt Injection Attacks on Agentic AI Frameworks

• ↑ supportsFrom Examples to Patterns: LLM-Generated Regular Expressions for Entity Extraction in Czech Clinical Texts

• ↑ supportsLIMIT: Less Is More for Instruction Tuning in Text-to-SQL

• ↑ supportsRecognition-Refusal Misalignment in LLMs: Why Models Answer Structurally Unanswerable Questions

• ↑ supportsBeyond Accuracy: ARIA-Rubrics for Evaluating Audio Reasoning in Large Audio Language Models

• ↑ supportsBelief-State Engine: Augmenting LLMs for Principled Planning Under Partial Observability

• ↑ supportsBLINDSPOT: A Benchmark for Safety and Refusal Calibration in Long-Horizon Tool-Using Agents

• ↑ supportsMulti-Agent Agentic Graph Learning via Structural Signatures

• ↑ supportsEviDx: Evidence-Aware Active Diagnosis with Scaffolded LLM Agents

• ↑ supportsHow Fast Do Agents Rot? An Empirical Study of Long-Horizon Degradation in LLM Agents for Production Decision-Making

• ↑ supportsStaying on the Attack Path: Structured State for Long-Horizon Automated Penetration Testing

• ↑ supportsLLMs Are Not Good Strategists, Yet Memory-Enhanced Agency Boosts Reasoning

• ↑ supportsEarth-Agent-Pro: Towards Real-World Full-Chain Earth Observation with Agents

• ↑ supportsS3Gym: Can LLMs Turn Self-Testing and Self-Judging into Self-Improvement?

• ↑ supportsVAKRA: Evaluating Multi-Hop Reasoning Across APIs and Retrieval Under Tool-Use Policies

• ↑ supportsUncertainty Quantification for LLM Agents: A Taxonomy, an Evaluation Protocol, and an Empirical Study

• ↑ supportsDataFoundry: Evolving Data Preparators via Recursive Self-Improvement

• ↑ supportsRepair or Resample? Rethinking Failure Debugging in LLM Multi-Agent Systems

• ↑ supportsTowards the Generalizability of Leveraging ChatGPT in APR via Self-enhancing: An Empirical Study

• ↑ supportsLearning Simple Test-Time Environments for LLM Web Agents

• ↑ supportsLLM-based Agents for Forecasting and Prediction: Methods, Training, Evaluation, and Applications

• ↑ supportsAlgoEvo: Self-Evolving Agentic Search for Automated Algorithm Discovery

• ↑ supportsAeroWeaver: An Embodied-Agent Harness for Weaving Aerial Skills into Distributed, Adaptive Swarm Execution

• ↑ supportsBridging Semantics and Physics with Constrained LLMs for Safe and Trustworthy Robotic Manipulation

• ↑ supportsFPGAgent: An LLM-Assisted Framework for Autonomous HLS Code Generation and Verification in FPGA Environments

• ↑ supportsFPGAgent: An LLM-Assisted Framework for Autonomous HLS Code Generation and Verification in FPGA Environments

• ↑ supportsUTP-Bench: Uncertainty-aware Travel Planning Benchmark

• ↑ supportsFrom Semantic Decisions to Feasible Trajectories: Self-Evolving LLM-Guided Optimal Control for Narrow-Space Parking

• ↑ supportsBenchmarking AI Agents for Hardware Design Automation via MCP Tool Calling

• ↑ supportsNutriBench-Kitchen: Benchmarking Embodied AI for Nutrition Management

• ↑ supportsGAVEL: Graph World Models for Verified and Efficient Long-Horizon LLM Task Planning

• ↑ supportsRollback the World, Keep the Reflection: Rollback-Induced Reflection for Long-Horizon LLM Agents

• ↑ supportsFrom Sequence to Structure: Relational Uncertainty Propagation for LLM Agents

• ↑ supportsFLARE: A Full-Lifecycle Dense Supervision Paradigm for Long-Horizon Coding Agents via Generative Reward Model

• ↑ supportsECLIPSE: Self-Evolving Stealthy Prompt Injection Attack against Long-Horizon Agentic Systems

• ↑ supportsRIDGE: Region-Informed Derivative-Guided Evidence Selection for Long Video Understanding

• ↑ supportsTemporal Tree of Thought: Reasoning-Guided Visual Cue Search for Long-Video Understanding

• ↑ supportsMarKey: Marginal Utility Guided Greedy Keyframe Selection for Long Video Understanding

• ↑ supportsVideoHarness-RSI: Recursive Harness Self-Improvement for Long-Video Understanding with Frozen Vision-Language Models

• ↑ supportsCredal Large Language Models for Semantic Commitment under Uncertainty

• ↑ supportsSkillMemo: Expert-guided Skill Memory Framework for Compositional Embodied Manipulation

• ↑ supportsAtomEgo: Exploring Ego-Robot Integration for Embodied Foundation Model Pretraining

• ↑ supportsReinforcement Learning for Real-Time Vision-Language-Action Policies

• ↑ supportsWorld-Model-Grounded LLM Planning for AUV and ASV Navigation Near Offshore Wind Farms

• ↑ supportsEMR: Self-Evolving Medical Multi-Agent System via Experience Mining and Reuse

• ↑ supportsActiveArena: Benchmarking and Understanding Active Perception in Robotic Manipulation

• ↑ supportsLightNav-0: Eliciting VLM Spatial Intelligence for Generalist Embodied Navigation

• ↑ supportsEvidence, Logic, and Compliance: Multi-Agent Structured Graph Reasoning with Expert Arbitration for Medical Referral

• ↑ supportsWhen Evidence Shapes Collaboration: Knowledge-Conditioned Topology Generation for Multi-Agent Systems

• ↑ supportsFrom Storage to Access: Verifiable Activation of Parametric Knowledge in LLMs via Explicit Priming and Implicit Reasoning

• ↑ supportsConvMem: Convolutional Memory for Long-Context Reasoning

• ↑ supportsM$^3$P-R1: Reinforcement Learning for Large Language Model Guided Multi-Modal Motion Planning via MIP Code Generation

• ↑ supportsSTEP: State-Aware Task Estimation and Planning with Multi-Modal LLMs for Human-Robot Collaboration

• ↑ supportsMoTE: Mixture of Task Experts for Multi-Task Video Understanding

• ↑ supportsMTAC-IFBench: Benchmarking Instruction-Following in Multi-Turn Agentic Coding

• ↑ supportsSAPO: Single-Rollout Autoregressive Policy Optimization for Agentic Reinforcement Learning

• ↑ supportsRideWay: Benchmarking Efficient Task Completion for Tool-Using Language Agents

• ↑ supportsHalluPrism: When Multimodal Uncertainty Should Diagnose, Not Decide

• ↑ supportsGetting the Parameters Right: A Difficulty-Graded Benchmark and Probe-Guided Training for LLM Tool Calls

• ↑ supportsMulti-Faceted Evaluation and Mitigation of Emotion Hallucinations in MLLMs

• ↑ supportsBridging Thought and Action: Taming Long-Horizon Instability in Open-Source LLM Agents with a MetaTool-Enhanced ROS Framework

• ↑ supportsCounterfactual Tests for Measuring Chain-of-Thought Faithfulness in Visual Language Models

• ↑ supportsWhat Guides the Agent? Adjudicating Unauthorized Behavior via Localizing Behavior-Guiding Instructions

• ↑ supportsAgenTeeth: A Model-Agnostic Framework for Suppressing Hallucination in Frozen Vision-Language Models on Dental X-Rays via Tool Evidence Injection

• ↑ supportsCAPTURE: Disentangling Preference Drift from Memory Poisoning in Personalized LLM Agents

• ↑ supportsHIL-UMI: Bringing Human-in-the-Loop Post-Training of Vision-Language-Action Models to Universal Manipulation Interface

• ↑ supportsTimeRLM: Recursive Language Models Enable Precise Anomaly Localization in Long-Context Time-Series

• ↑ supportsBridge3D: Enabling Vision-Language-Action Models to See and Act in 3D

• ↑ supportsClosing the Consistency Gap: Self-Evolving Agents That Learn to Stay on Course

• ↑ supportsVLA-Precision: Asymmetric Co-Bootstrapping for Efficient Real-World Online RL of Vision-Language-Action Models

• ↑ supportsIntegrating Crash Report Mining and LLMs for Bug Localization and Repair: An Industrial Report

• ↑ supportsLeveraging Low-Level Symbolic Competences for Unsupervised Grounding in Hallucination Detection

• ↑ supportsLeveraging Low-Level Symbolic Competences for Unsupervised Grounding in Hallucination Detection

• ↑ supportsJust Ask for Calibration: Strategies for Eliciting Calibrated Confidence Scores from Language Models Fine-Tuned with Human Feedback

• ↑ supportsFRAMEWORKERS: A Dynamic Multi-Agent Framework for AI-Generated Video Production

• ↑ supportsLongGuard: Mechanistic Analysis and Training-Free Mitigation of Long-Context Failure in Safety Guardrails

• ↑ supportsReplacing Training with Memory: Listwise Selection for Text-to-SQL

• ↑ supportsCoalition-Aware Skill Reliability for Self-Evolving Agents

• ↑ supportsCoalition-Aware Skill Reliability for Self-Evolving Agents

• ↑ supportsBeyond Language Priors: Diagnosing and Fixing Visual-Origin Hallucinations in Multimodal LLM

• ↑ supportsBeyond Language Priors: Diagnosing and Fixing Visual-Origin Hallucinations in Multimodal LLM

• ↑ supportsSKILL.state: Scalable Long-Horizon Agent Skills

• ↑ supportsToolRobustBench: Stage-Wise Perturbation Evaluation and Failure Diagnosis for Tool-Calling Agents

• ↑ supportsToolRobustBench: Stage-Wise Perturbation Evaluation and Failure Diagnosis for Tool-Calling Agents

• ↑ supportsAgent Memory Distillation: Empowering Small LLM Agents with Hierarchical Teacher Memory

• ↑ supportsMitigating LLM sycophancy with RL-based fine-tuning: Bayesian Truth Serum approach

• ↑ supportsMitigating LLM sycophancy with RL-based fine-tuning: Bayesian Truth Serum approach

• ↑ supportsHiRS-Agent: A Hierarchical Multi-Agent System for Reliable Long-Horizon Remote Sensing Task Solving

• ↑ supportsSmall Reasoning Models are Instruction Followers in Function Calling

• ↑ supportsDo Large Language Models Play Six Degrees of Separation? Measuring Topological Compression in Long-Context Manifolds

• ↑ supportsAttention Dispersion as a Diagnostic Signal for Hallucination in Large Language Models

• ↑ supportsVoxZip: Semantic-Anchored Temporal KV Cache Compression for Long-Context Audio Inference

• ↑ supportsVox-Infinity: Benchmarking the Limits of Long-Context Spoken Language Models

• ↑ supportsNeuro-symbolic PRM: Enhancing Scientific Reasoning via Structured Traces and Symbolic Verification

• ↑ supportsBeyond Retrieval: Progressive Latent Memory Evolution for Streaming Video Understanding

• ↑ supportsShallowStream: Index Shallow then Answer Deep for Streaming Video Understanding

• ↑ supportsFlashExtract: A Framework for Data Extraction by Examples

• ↑ supportsBeyond Fluent Generation: A CPU Reliability Benchmark for MCP-Style Tool Calling in Sub-2B Small Language Models for Edge Deployment

• ↑ supportsMulti-modal Synthesis of Regular Expressions

• ↑ supportsXPath Agent: An Efficient XPath Programming Agent Based on LLM for Web Crawler

• ↑ supportsFrontiers in FinTech: Multimodal Foundation Models for Financial Reporting and Decision Science

• ↑ supportsORCH: Organizational Principles Enable Collective Intelligence in Embodied AI

• ↑ supportsCIT-CAD: Constraint Intent Tree-based CAD Code Generation and Verification

• ↑ supportsTimeThink: Eliciting Compositional Reasoning in Timeseries Large Language Models

• ↑ supportsLexAgentHallu: A Hierarchical Benchmark for Profiling Hallucinations in Legal Agents

• ↑ supportsActionable Hallucination Detection: Translating Latent Uncertainty into Agentic Critique

• ↑ supportsUniversal Defenses for Tool-Integrated LLM Agents Against Adversarial Attacks

• ↑ supportsActGuard: Pre-execution Action Auditing against Indirect Prompt Injection in LLM Agents

• ↑ supportsCoER: Defending against Adaptive Indirect Prompt Injection via Adversarial Co-Evolution and Refinement

• ↑ supportsEvoSafeHarness: Evolving Model- and Domain-Specific Harnesses for Securing Agents

• ↑ supportsROPE: Routed Origin Policy Enforcement against Indirect Prompt Injection

• ↑ supportsReachability-Based Capability Confinement for LLM Agents under Indirect Prompt Injection

• ↑ supportsEvolveTrade: Experience-Driven Policy Refinement for Self-Evolving LLM Trading Agents

• ↑ supportsEviAnchor: Mitigating Hallucinations in Large Vision-Language Models via Regional Visual Evidence Compensation

• ↑ supportsDoes Playing it Safe Count as Faithfulness? Reassessing LVLM Hallucination Mitigation Methods

• ↑ supportsHarnessVLN: Unifying Training-Free Embodied Navigation through an Agent Harness

• ↑ supportsNeural Generation of Regular Expressions from Natural Language with Minimal Domain Knowledge

• ↑ supportsSemantics-Guided Automatic Tensorization for Multiobjective Evolutionary Algorithms: A Multi-Agent Framework

• ↑ supportsLIBERO-RECOVER: Beyond Task Success Towards Failure Recovery in Robotic Manipulation Models

• ↑ supportsGALA: Geometry-Aware Latent Action Modeling for Vision-Language-Action Model Pretraining across Embodiments

• ↑ supportsLIBERO-RECOVER: Beyond Task Success Towards Failure Recovery in Robotic Manipulation Models

• ↑ supportsValidating, Not Sampling: Region-Level Robustness of Vision-Language and Vision-Language-Action Models

• ↑ supports4DSynth: Controllable Procedural World Synthesis for Dynamic Embodied Simulation

• ↑ supportsWorldReward: Reward Modeling for Camera-Conditioned World Models

• ↑ supportsEmbodied-Navigator: Point, Think, Memorize, and Align for Efficient Navigation

• ↑ supportsSafe Task Planning with Long-Term Graph Memory for Embodied Agents

• ↑ supportsEgoPathBench: Evaluating Zero-Shot Egocentric Waypoint Decision-Making in Vision-Language Models

• ↑ supportsEvaluating Large Language Models for Forced Outage Risk Prediction: Benefits and Comparison to Machine Learning

• ↑ supportsExploring Large Language Models for Communication Games: An Empirical Study on WerewolfThis source: Exploring Large Language Models for Communication Games: An Empirical …How much the field cites it — heavily cited in the last 12 months59 in the last 12 months · 312 totalpublished 2023checked 2026-09-04click for Semantic Scholar

• ↑ supportsStop Means Stop: Measuring and Repairing the Enforcement Gap in Agent-Framework Control Primitives

• ↑ supportsHalluPeer: A Taxonomy-driven Benchmark for Detecting Hallucinations in Scientific Peer Reviews

• ↑ supportsHalluPeer: A Taxonomy-driven Benchmark for Detecting Hallucinations in Scientific Peer Reviews

• ↑ supportsScientistTwo: Pioneering the Human Knowledge Frontier with Autonomous AI

• ↑ supportsLarge Language Models in Resolving Contextual Knowledge Conflicts
• ↑ supportsAdaptive Chameleon or Stubborn Sloth: Revealing the Behavior of Large Language Models in Knowledge ConflictsThis source: Adaptive Chameleon or Stubborn Sloth: Revealing the Behavior of Large …How much the field cites it — heavily cited in the last 12 months148 in the last 12 months · 382 totalpublished 2023checked 2026-09-04

• ↑ supportsSWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering
• ↑ supportsI Improved 15 LLMs at Coding in One Afternoon. Only the Harness Changed.

• ↑ supportsLocAgent: Graph-Guided LLM Agents for Code Localization

• ↑ supportsThe Reversal Curse: LLMs trained on "A is B" fail to learn "B is A"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 months174 in the last 12 months · 530 totalpublished 2023checked 2026-09-04

• ↑ supportsWe Have a Package for You! A Comprehensive Analysis of Package Hallucinations by Code Generating LLMsThis 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 months80 in the last 12 months · 106 totalpublished 2024checked 2026-09-04

• ↑ supportsEvaluating Large Language Models Trained on CodeThis source: Evaluating Large Language Models Trained on CodeHow much the field cites it — very heavily cited in the last 12 months1000+ in the last 12 months · 11293 totalpublished 2021checked 2026-09-04count capped at 1000 by the fetchclick for Semantic Scholar

• ↑ supportsNot what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt InjectionThis 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 months1000+ in the last 12 months · 1870 totalpublished 2023checked 2026-09-04count capped at 1000 by the fetch
• ↑ supportsAdaptive Chameleon or Stubborn Sloth: Revealing the Behavior of Large Language Models in Knowledge ConflictsThis source: Adaptive Chameleon or Stubborn Sloth: Revealing the Behavior of Large …How much the field cites it — heavily cited in the last 12 months148 in the last 12 months · 382 totalpublished 2023checked 2026-09-04

• ↑ supportsRetrieval-Augmented Generation for Knowledge-Intensive NLP TasksThis source: Retrieval-Augmented Generation for Knowledge-Intensive NLP TasksHow much the field cites it — very heavily cited in the last 12 months1000+ in the last 12 months · 17840 totalpublished 2020checked 2026-09-04count capped at 1000 by the fetch

• ↑ supportsThe new rules of context engineering for Claude 5 generation models

• ↑ supportsHarness Engineering — Agent = Model + Harness: The 6-Layer Production Playbook
• ↑ supportsHashimoto's rule for AI agents is that every mistake becomes a permanent fix

• ↑ supportsContextPilot: Teaching Agents for Proactive Context Management via Fine-grained RL

• ↑ supportsSelf-Evaluating LLMs for Multi-Step Tasks: Stepwise Confidence Estimation for Failure Detection

• ↑ supportsSame Task, More Tokens: the Impact of Input Length on the Reasoning Performance of Large Language ModelsThis 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 months104 in the last 12 months · 238 totalpublished 2024checked 2026-09-04click for Semantic Scholar

• ↑ supportsJudging LLM-as-a-Judge with MT-Bench and Chatbot ArenaThis source: Judging LLM-as-a-Judge with MT-Bench and Chatbot ArenaHow much the field cites it — very heavily cited in the last 12 months1000+ in the last 12 months · 10936 totalpublished 2023checked 2026-09-04count capped at 1000 by the fetchclick for Semantic Scholar

• ↑ supportsDetecting Object Hallucinations in Large Vision-Language Models via Cross-Modal Attention Drifts and Mask-Based Verification

• ↑ supportsSame Attention, Different Truths: Put Logit-Lens over Visual Attention to Detect and Mitigate LVLM Object Hallucination

• ↑ supportsMLLMs Hallucinate when Information Distribution Drifts in Synergy Heads

• ↑ supportsLook Before You Leap: Factual Decoding with Internal Attribution Signals

• ↑ supportsNeuroActiSep: Detecting Factual Hallucinations from Feed-Forward Neurons in a Single Pass

• ↑ supportsHallucination Mitigation for Large Vision-Language Models via Implicit Feature Stabilization

• ↑ supportsWhat Do Hallucinations Reveal About Multimodal Reasoning? Diagnosing Visual Grounding Failures via Contrastive Decoding Probes

• ↑ supportsRVSD: Retrieval Vision Sparse Decoding for Mitigating Visual Hallucinations in Large Vision-Language Models

• ↑ supportsReWEIGH the Evidence: Calibrating Token-Level Ordinal Visual Evidence to Mitigate Hallucinations in Large Vision-Language Models

• ↑ supportsReWEIGH the Evidence: Calibrating Token-Level Ordinal Visual Evidence to Mitigate Hallucinations in Large Vision-Language Models

• ↑ supportsTest-Time Hallucination Control in Large Vision-Language Models

• ↑ supportsBeyond Global Editing: Per-Instance Disentangled Subspaces for Training-Free Hallucination Mitigation in LVLMs

• ↑ supportsWiener Representation Filtering for VLM Hallucination Suppression

• ↑ supportsFM-Bench: A Benchmark for Long-Horizon Management with Competing Agents

• ↑ supportsFM-Bench: A Benchmark for Long-Horizon Management with Competing Agents

• ↑ supportsToward Self-Adaptive Physical AI: Can LLM Agents Manage Long-Horizon Physical Tasks?

• ↑ supportsA Control-Theoretic Approach for Resource-Aware Consensus in Multi-Agent AI

• ↑ supportsAuditable Emergency Triage for Maternal and Newborn Care in India

• ↑ supportsE-Commerce Bench: Evaluating LLM Agents on Long-Horizon Autonomous Business Operation

• ↑ supportsNemotronLabs VoiceChat: An Open Full-duplex Speech-to-Speech Model with Tool Calling Capabilities

• ↑ supportsHypoEvolve: Genetic Algorithms Enable Multi-Agent LLMs to Discover Scientific Hypotheses

• ↑ supportsSemantic Uncertainty-Guided Orchestration in Hierarchical Multi-Agent Systems

• ↑ supportsToward Meaningful Transparency for AI Chatbots: Disclosing Persuasive Intent Reduces Persuasion

• ↑ supportsPerceived Political Bias in LLMs Reduces Persuasive Abilities

• ↑ supportsAgentic ML Exploration (A-MLE) for Ads Ranking

• ↑ supportsAn Iterative LangGraph Agent for Text-to-SQL: Natural Language Access to the Chicago Crime Database

• ↑ supportsTraining-Free Inference-Time Self-Reflection and Cost-Bounded Early Stopping for Large Language Models

• ↑ supportsTranslating the Translator: Decomposing the Cost of English-Forced Inter-Agent Communication

• ↑ supportsAgentopia on a Consumer GPU: A Reduced-Scale Long-Horizon Port with an 8B Model

• ↑ supportsTowards Fully Automated Medical Imaging Code Generation via Validation-based Context Engineering

• ↑ supportsKnowledge-Verified Emergent Deception in LLM Agents Under Conflicting Incentives

• ↑ supportsKnowledge-Verified Emergent Deception in LLM Agents Under Conflicting Incentives

• ↑ supportsHarness Engineering — Agent = Model + Harness: The 6-Layer Production Playbook
• ↑ supportsLarge Language Models Cannot Self-Correct Reasoning YetThis source: Large Language Models Cannot Self-Correct Reasoning YetHow much the field cites it — very heavily cited in the last 12 months503 in the last 12 months · 1164 totalpublished 2023checked 2026-09-04
• ↑ supportsMaintainability sensors for coding agents

• ↑ supportsArchitecting the Secure AI-SOC: A Neurosymbolic Framework for Pipeline Integrity and Threat Mitigation

• ↑ supportsEnforcing Narrative Reliability and Epistemic Pacing in LLM-Driven Detective Games via Structured Knowledge Trees

• ↑ supportsAudioICL-Bench: A Benchmark for Large Audio Language Model In-Context Learning

• ↑ supportsDiscrete vs. Continuous: A Comprehensive Study of Unified Audio Understanding in LALMs

• ↑ supportsOmniHallu: Unified Hallucination Detection for Cross-Modal Comprehension and Generation in Multimodal Large Language Models

• ↑ supportsDecomposed Prompting Does Not Fix Knowledge Gaps, But Helps Models Say "I Don't Know"

• ↑ supportsEvaluating Confidence-Gated Retrieval with Matched Trajectory Replay

• ↑ supportsReliability Challenges in Diffusion Vision-Language Models

• ↑ supportsPreference Data Selection for Mitigating the Alignment Tax in Large Language Models

• ↑ supportsDecoupling Planning and Control for Instructable Agents

• ↑ supportsCoCoBench: A Cooperative Coordination Benchmark for Embodied Multi-Agent Task Planning

• ↑ supportsHeard but Not Heeded: Paralinguistic Information Encoding and Loss in Audio-Language Models

• ↑ supportsEmpirical Evaluation of Open-Source Large Language Models for Retrieval-Augmented Generation in ESG Domain

• ↑ supportsTimeLitmus: A Diagnostic Benchmark for Cross-Modal Understanding and Explanation Faithfulness in Event-Conditioned Time-Series Prediction

• ↑ supportsWorldBench: Culturally Grounded Benchmark for Multilingual Agents

• ↑ supportsEvaluating the Capabilities of LLMs for Persuasive Dialogue

• ↑ supportsLarge language models can effectively convince people to believe conspiracies

• ↑ supportsUniProbe: A Learnable Token-Level Hallucination Detector for Large VLMs using Multi-Structural Internal Representations

• ↑ supportsBias Amplification in Multi-Agent Network: How Biased Agents Shape Opinions and Rhetoric

• ↑ supportsStable-MM-R1: Anchoring Multimodal Reasoning Dynamics via Entropy-Guided Stratification

• ↑ supportsBoosting LLM Exploration via Weak-Model Guidance in RLVR

• ↑ supportsBayesian Partner Modelling enables Adaptive Replanning for LLM Coordination

• ↑ supportsTraceML: An Empirical Analysis of Human-Agent Planning in Machine Learning Development

• ↑ supportsProgrammable World Model

• ↑ supportsCo-RL: Unsupervised Reasoning Emerges from Diverse Cohort in Multi-agent RL

• ↑ supportsTAD: Token-Adaptive Contrastive Decoding with Confidence-Guided Gating for Hallucination Mitigation in Large Audio-Language Models

• ↑ supportsTargeting the Attention Heads Behind Object Hallucination in LLaVA

• ↑ supportsTargeting the Attention Heads Behind Object Hallucination in LLaVA

• ↑ supportsEvaluating and Improving Evidence-Grounded Fact-Checking in LLMs via Multi-Round Evidence Ablation

• ↑ supportsFinding Where the Buck Stops: An Automated Failure Attribution-Based Reflection Framework for Multi-Agent Collaboration

• ↑ supportsDiscovering Efficient and Explainable Communication Topologies for LLM-based Multi-Agent Systems via Causal Inference

• ↑ supportsLikelihood-Constrained Acoustic Reranking for Training-Free Hallucination Mitigation in LLM-Based ASR

• ↑ supportsBetter Understanding, Better Fixes? A Study of Hallucination in LLM-based Automated Program Repair

• ↑ supportsRefine After Generation: Toward Correct and Concise Patches in LLM-based Program Repair

• ↑ supportsSTEVE: Stabilizing Textual Gradient-Based Prompt Optimization via Error-Driven Refinement and Regularized Verification

• ↑ supportsMGAL: A Multilingual Granularity-Aware Long-Context Benchmark

• ↑ supportsCivBench: A Long-Horizon Benchmark for Tool-Mediated Agents in Civilization VI

• ↑ supportsViD: Vision-Dominant Gender Bias Mitigation for Large Vision-Language Models

• ↑ supportsIn-Place Instruction Following in Diffusion Language Models

• ↑ supportsRemember and Reweight: Enhancing Multi-Agent Debate with Experience Memory and Confidence Estimation

• ↑ supportsAssembling the CREW: A Collaborative Multi-agent Reinforcement Learning Framework for Automated Related Work Generation

• ↑ supportsAgents That Model Agents: Five Principles Toward a Theory of Mind for 6G Networks

• ↑ supportsLearning What to Retain: Gated-Memory Routing for Efficient Collaboration in Multi-Agent LLM Systems

• ↑ supportsHallucination as Context Drift: Synchronization Protocols for Multi-Agent LLM Systems

• ↑ supportsProgRouter: Online Progress-Guided Orchestration for Multi-Agent LLM Workflows under Quality-Cost Tradeoffs

• ↑ supportsTheseus in the Graph: Towards Traceable Multi-Hop Graph Navigation

• ↑ supportsUncovering and Mitigating Aggregation-Induced Reward Hacking in Multi-Reward Reinforcement Learning

• ↑ supportsLOCI: A Locator-Critic with Refinement Loop

• ↑ supportsWhen Guardrails Look Effective: Construct Validity Failures in LLM Agent Commerce Evaluation

• ↑ supportsEvaluating LLMs on Conversational Text-to-SQL under Chain Ambiguity and Intent Drift

• ↑ supportsDo LLMs Beat Nash? Testing Decentralized Coordination in Self-Play Multi-Agent Games

• ↑ supportsACE: A Self-Correcting Agentic Canvas Editor for Multi-Slide Presentation Automation

• ↑ supportsSweet Talkers: How Query Formulation Shapes Sycophancy in Romantic Relationship Advice

• ↑ supportsDynamic Alignment Compensation for Hallucination Mitigation in Large Vision-Language Models

• ↑ supportsDynamic Alignment Compensation for Hallucination Mitigation in Large Vision-Language Models

• ↑ supportsPrediction of Prediction (PoP): Inter-Layer Activation Fusion for Single-Pass Hallucination Detection in Large Language Models

• ↑ supportsSycophancy Suppression Can Impair Rational Updating: Anti-Sycophancy Should Preserve the Ability to Update

• ↑ supportsTowards a Belief-Based World Model for LLM Agents

• ↑ supportsBeyond Similarity: Coverage-Aware Prompt Selection for Time Series Forecasting with LLMs

• ↑ supportsCounterfactual Anatomy-guided Spatial-Temporal Decoding for Annotation-Free Hallucination Mitigation in Medical VLMs

• ↑ supportsDetecting and Repairing Hallucinations in Retrieval-Augmented Generation

• ↑ supportsLess Is Personal: Learning Minimal Sufficient User Profiles for Personalized Language Models

• ↑ supportsMR-IQA-2: Faithful Image Quality Reflection via Fine-Grained Credit Assignment

• ↑ supportsMR-IQA-2: Faithful Image Quality Reflection via Fine-Grained Credit Assignment

• ↑ supportsCHARM: Character Hallucination for Multicultural Role Play Benchmark

• ↑ supportsHype Meets Reality: Large Language Models as Mutators in Search-based Automated Program Repair of Simulink-Stateflow Models

• ↑ supportsGuaranteeing Faithful Evidence Extraction in Speculative Retrieval-Augmented Generation

• ↑ supportsBelief Cascades Drive Persuasion in LLM Agent Networks

• ↑ supportsτ-bench: A Benchmark for Tool-Agent-User Interaction in Real-World DomainsThis 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 months889 in the last 12 months · 1075 totalpublished 2024checked 2026-09-04

• ↑ supportsτ-bench: A Benchmark for Tool-Agent-User Interaction in Real-World DomainsThis 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 months889 in the last 12 months · 1075 totalpublished 2024checked 2026-09-04

• ↑ supportsTowards Embodied Air-Ground Cooperative Object Search: Benchmark, Dataset and Agentic Method

• ↑ supportsLost in Speech: Trilingual Spoken Hallucination Detection Across Audio and Transcripts

• ↑ supportsCounterfactual Anatomy-guided Spatial-Temporal Decoding for Annotation-Free Hallucination Mitigation in Medical VLMs

• ↑ supportsDSE-VTG: Dual-Side Enhancement for Training-Free Video Temporal Grounding

• ↑ supportsDSE-VTG: Dual-Side Enhancement for Training-Free Video Temporal Grounding

• ↑ supportsBelief Without Behavior: Measuring the Translation of Theory of Mind into Coordinated Social Action in Vision-Language Models

• ↑ supportsBelief Without Behavior: Measuring the Translation of Theory of Mind into Coordinated Social Action in Vision-Language Models

• ↑ supportsRubrics as Visual-Repair Context for Self-Evolving UI-to-Code Generation

• ↑ supportsHINT-Plan: Human Intention-Aware Robot Task Planning in Context-Rich Environments using Vision Language Models

• ↑ supportsBeyond Vector Similarity: Hierarchical Context-Aware Graph RAG vs Standard RAG in Enterprise Code Migration

• ↑ supportsBetter Understanding, Better Fixes? A Study of Hallucination in LLM-based Automated Program Repair

• ↑ supportsR-Tuning: Instructing Large Language Models to Say `I Don't Know'

• ↑ supportsTraining Verifiers to Solve Math Word ProblemsThis source: Training Verifiers to Solve Math Word ProblemsHow much the field cites it — very heavily cited in the last 12 months1000+ in the last 12 months · 10385 totalpublished 2021checked 2026-09-04count capped at 1000 by the fetchclick for Semantic Scholar

• ↑ supportsSweRank: Software Issue Localization with Code Ranking

• ↑ supportsBenchmarking Knowledge Editing using Logical Rules

• ↑ supportsLLMs Have Made Failure Worth Publishing

• ↑ supportsLanguage Models (Mostly) Know What They Know

• ↑ supportsLLM-Generated Ads: From Personalization Parity to Persuasion Superiority

• ↑ supportsFActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text GenerationThis source: FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long…How much the field cites it — very heavily cited in the last 12 months697 in the last 12 months · 1643 totalpublished 2023checked 2026-09-04click for Semantic Scholar