WikiTrace, 기억 출처 연결로 LLM 에이전트 메모리 오류 감소
Don't Just Trust Your Memory: Evidence-Linked Memory Reduces Memory-Induced Degradation in LLM Agents
- 매체
- Hugging Face
- 게시
- 중요도
- 3/5
- 화제 지수
- 19
한국어 요약
외부 메모리가 LLM 에이전트의 기억 유도 성능 저하 문제(과거 작업에서 배운 잘못된 교훈을 따르거나 오독하는 경우)를 야기할 수 있다는 점을 지적하고, 각 교훈을 원래 궤적과 연결해 에이전트가 검증할 수 있도록 하는 증거 연결 메모리 시스템 WikiTrace를 제안했다. 5개 에이전트 벤치마크에서 기존 메모리 방식보다 지속적으로 우수한 성능을 보였고 메모리 유도 성능 저하도 감소시켰다.
같은 소식, 다른 매체 · 1곳
원문 발췌 · English
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 trajectory. Specifically, motivated by the finding that a trajectory often still holds the evidence needed to catch an erroneous lesson, WikiTrace stores each lesson as a concise insight linked to a summary of why its trajectory succeeded or failed and to the raw trajectory itself. Then, on a new task, the agent starts from all insights and, whenever one lacks details needed to act, conflicts with another, or comes from a failed task, descends through its links with terminal tools to fill in missing details or correct the insight before acting. We validate WikiTrace on five agentic benchmarks, showing that it consistently outperforms existing memory approaches and a baseline given the same insights alone, while also reducing memory-induced degradation. Our code is available at https://github.com/yukyeongleee/wikitrace