arXiv 2610.27406 · cs.AI · 2026-10-19
More Memory, Worse Agents: Error Reproduction and Anti-Persistence in LLM Agents
Ruhan Wang, Kishan Panaganti, Dongruo Zhou
Indiana University Bloomington
在最新榜 #390 本站收录于 2026-10-26
一句话要点
论文指出智能体把经验抽象成规则和技能存进记忆时，错误会经「抽象、执行、再抽象」循环不断再生，称为错误复现，使错误比直接复用错误知识持续得更久。
Agents that store abstracted rules and skills in memory can suffer "error reproduction": faulty abstractions shape new trajectories that are re-abstracted into the same errors, making them persist beyond direct reuse.
阅读 arXiv 原文 PDF Hugging Face 讨论
主题与学科
同主题：智能体
- Raven: The Harness of Harnesses for Composable Agentic Intelligence ▲748
- False Frontiers: Diagnosing and Mitigating Co-Cheating in Self-Evolving Search Agents ▲642
- Omni-IO Skills: Harnessing Your Agent Omni-Native ▲485
- BizAgentBench: Unveiling Hidden Challenges in Deploying Long-Horizon Agents for Real-World Business ▲388
- Player-1: Learning to Play from Synthetic Experience ▲347
同主题：大语言模型
- Jeva: System One Models from First Principles 2026-10-13 · ▲371
- Post-Training Leaves Behavioral Shadows on Unrelated Decisions 2026-09-24 · ▲273
- WeVisOne-VL: Unified Visual Perception from Objects to Pixels 2026-10-22 · ▲247
- Thinking Inertia: LLMs Keep Thinking When Told Not To 2026-10-08 · ▲241
- OmniEdu: Open Foundation Models for Learning and Teaching 2026-09-19 · ▲240
数据说明
元数据来自 arXiv API（已核实）；点赞来自 Hugging Face 每日论文；引用来自 Semantic Scholar。最近刷新 2026-10-26。
要点由本站根据摘要自写，不转载摘要原文，请阅读原文。