When Successful Memories Mislead Embodied Agents:Memory Adaption For Task-Conditioned Execution

arXiv:2609.35808 · cs.CL, cs.AI · Submitted 2026-09-20 · Read on arXiv

cs.CL, cs.AI

Submitted: 2026-09-20

Updated: 2026-09-20

Terminology

• Adaptation — 16× in this paper · explained in 1 episode
• Ablation — 6× in this paper · explained in 1 episode
• Benchmark — 5× in this paper · explained in 2 episodes
• Accuracy — 2× in this paper · explained in 1 episode
• Distillation — 2× in this paper · explained in 2 episodes
• Robustness — 2× in this paper · explained in 5 episodes
• Trace — 2× in this paper · explained in 2 episodes
• TravelPlanner Final Pass Rate — 2× in this paper
• AI Agents — 1× in this paper · explained in 2 episodes
• Action Space — 1× in this paper · explained in 1 episode
• Agent Memory — 1× in this paper · explained in 1 episode
• Alternation — 1× in this paper · explained in 1 episode
• Continual Learning — 1× in this paper · explained in 2 episodes
• Embeddings — 1× in this paper · explained in 2 episodes
• Grounding — 1× in this paper · explained in 3 episodes
• Memory Adaptation for Task-Conditioned Execution — 1× in this paper
• Provenance — 1× in this paper · explained in 4 episodes
• Verification — 1× in this paper · explained in 2 episodes

Sources

• Agent Workflow Memory
• Get Experience from Practice: LLM Agents with Record & Replay
• Memp: Exploring Agent Procedural Memory
• Qwen2.5 Technical Report
• The Compliance Trap: Diagnosing How AI Agents Consume Conflicting Memory
• When Continual Learning Moves to Memory: A Study of Experience Reuse in LLM Agents
• Grounding Agent Memory: Environment-Probing Curation for Enterprise Agents
• The Trap of Trajectory: Towards Understanding and Mitigating Spurious Correlations in Agentic Memory

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering