arXiv 2610.29357 · cs.CL · 2026-10-21
Memory-Centric Continual Learning for AI Agents
Dongfang Li, Zhuoen Chen, Bonian Jia, Zixuan Liu, Zhengxuan Lu, Can Deng, Yukun Shi, Yuhang Meng 等 28 人
SLAI-AITP
在最新榜 #328 本站收录于 2026-10-24
一句话要点
记忆中心的持续学习（MCCL）主张：智能体的外部记忆不该只当被动检索缓存、按能否回忆事实来评，而应看它能否改进以后的行动，让基于基座模型的智能体在长期部署中真正从经验里持续学习。
Memory-Centric Continual Learning (MCCL) argues agent memory should be judged by whether it improves future actions, not merely what it retrieves, turning external memory from a passive cache into a driver of genuine continual learning for long-deployed foundation-model agents.
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。