multimodal-llm-acts-decision-core-simulated-humanoid-reacting-sudden CLM-0620When a multimodal LLM acts as the decision core of a simulated humanoid reacting to sudden household hazards, picking the correct reaction primitive does not mean the reaction is executable: even on correctly classified scenes, hands land a median 0.48 m from the true impact point, 89% of misses fall short, and in 49% of those decisions the body never steps forward and stands beyond arm's reach.
Capability: Turning plans into physical action
Observed on
Seven zero-shot MLLMs, one frozen ~0.6 s multi-view observation, open-loop committed plan (walking command plus hand keyframes) executed by a pre-trained whole-body controller in r.
Sources
- Measured over 2,138 scene-model decisions with simulator-derived impact points; separates action label from endpoint distance, but ground truth is simulation-only, the plan is open-loop, and the arm-reach shortfall is partly attributable to the scripted upper-body/walking controller rather than the model alone.
Disagreeing is the most useful thing you can do here. Nothing on this page waits for a reviewer: the counts above move when evidence lands, and every source stays attached with who brought it.
Related claims
- In LLM multi-agent systems that reflect after failure, restricting reflection to the single agent responsible for the first incorrect step — located by a trained step-level correctness scorer and paired with a counterfactually generated corrected step — raises task success more than having every agent reflect on the trajectory, because reflections written by agents that behaved correctly enter their memory as misleading guidance for later tasks.Getting more from several models than from one · reviewed by AI
- In embodied environments with high-frequency action spaces (Atari, Minecraft, Crafter, DMLab, Overcooked, Pico Park, MindCraft), pairing a frozen instruction-tuned VLM that emits sparse text instructions with a small world-model controller trained to follow them scores higher than either the same VLM emitting low-level actions directly or the same controller running without instructions, and the gain depends on the instructions carrying semantic content — random-string instructions score no better than no instructions at all.Turning plans into physical action · reviewed by AI
- For LLM-driven robot manipulation where every tool call is schema-validated and every motion kinematically and collision-checked before execution, execution-time recovery mechanisms (retrying a failed plan with an alternative candidate, resetting to a collision-checked safe pose between stages) contribute more to end-to-end task success than canonical action sequencing, because most residual failures are transient planning or IK failures rather than wrong orderings.Turning plans into physical action · reviewed by AI
- For long-horizon embodied task planning where a symbolic model defines action preconditions and effects, correcting a violated plan by edits the action model itself implies (inserting the missing navigate or open) raises plan success more per LLM call than returning the violation to the LLM for replanning, and the gain persists for frontier models as well as compact ones.Planning a sequence of actions before acting · reviewed by AI
- When a document image states multi-step selection constraints in narrative text and the supporting numbers sit in several charts, multimodal models degrade steadily as either the number of logical hops (2 to 5) or the number of charts (2 to 6) grows, with the best model reaching 62.83% overall against over 90% for human annotators.Carrying a chain of inference through to its conclusion · reviewed by AI
Notes
Drafted from the paper by a model and filed unreviewed. Visible here so it can be read, not because anyone has vouched for it: it does not move any technique's standing and does not count toward the internal scorecard. Drafted confidence: medium. Falsifier as drafted: A model whose action-choice accuracy on these scenes is matched by endpoint distances within reach (and whose base motion closes the gap), showing correct labels do carry grounded execution.