About this paper
WikiTrace links each distilled lesson to its source trajectory and rationale, enabling LLM agents to verify and correct memories before acting, improving performance and reducing memory-induced degradation across agentic benchmarks.
External memory enables LLM agents to improve from experience by distilling trajectories of past tasks into concise lessons for new tasks. However, memory can also lead to memory-induced degradation, where an agent fails on tasks it would solve without memory, often because it follows a lesson that is incorrect, or misapplies or misreads a valid one. This is because lessons are inferred from trajectories labeled only with task success or failure, yet are typically provided without the trajectories they came from, leaving the agent no way to check them. To address this, we introduce WikiTrace, an evidence-linked memory system designed to let agents check each lesson against its original…
LLM agentsexternal memorymemory-induced degradationevidence-linked memory systemtrajectorieslessonsinsightsterminal toolsagentic benchmarks
- Upvotes
- 37
- Authors
- 4
- Published
- Nov 10, 2026
Summary and abstract excerpt via Hugging Face Papers ↗ · arXiv.
Trending history
Don't Just Trust Your Memory: Evidence-Linked Memory Reduces Memory-Induced Degradation in LLM Agents was first seen on Hugging Face · Daily papers on Nov 11, 2026. Since then it has appeared in 23 checks on 3 different days. Its best position was #1 of 30, reached on Nov 12, 15:28 UTC. It dropped off the list after Nov 13, 05:28 UTC.