titleDon't Just Trust Your Memory: Evidence-Linked Memory Reduces Memory-Induced Degradation in LLM Agents
authorsYukyeong Lee, Yumin Choi, Jinheon Baek, Sung Ju Hwang
date2026-11-10
venuearXiv (preprint, not peer reviewed)
idarXiv:2611.14320
affiliationKAIST AI
upvotes61 (Hugging Face Daily Papers, 2026-11-13)
linksabs pdf hf code
cite
primerMemory for AI agents
relatedOmniShowcase: Omnidirectional Subject-Consistent Video Generation from Multi-View Images
Look Only When Needed: Certificate-Guided Visual Routing for Efficient Diffusion VLMs
Language Models Can Control Their Own Attention
OmniRetrieval: Unified Retrieval across Heterogeneous Knowledge Sources
GRACE: Generation-aware latent compression for efficient video generation
abstractExternal 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

bibtex

@misc{lee2026don,
  title={Don't Just Trust Your Memory: Evidence-Linked Memory Reduces Memory-Induced Degradation in LLM Agents},
  author={Yukyeong Lee and Yumin Choi and Jinheon Baek and Sung Ju Hwang},
  year={2026},
  eprint={2611.14320},
  archivePrefix={arXiv},
  url={https://arxiv.org/abs/2611.14320}
}