arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2602.02369cs.AIcs.LG
收藏

Live-Evo: 从连续反馈中在线进化智能记忆

Live-Evo: Online Evolution of Agentic Memory from Continuous Feedback

Oregon State University(俄勒冈州立大学);AG2 AI(AG2人工智能);Penn State University(宾夕法尼亚州立大学)

Yaolun Zhang, Yiran Wu, Yijiong Yu, Qingyun Wu, Huazheng Wang

AI总结:

Live-Evo通过在线进化记忆系统,在连续反馈中提升任务性能和市场收益。

摘要:

大型语言模型(LLM)代理越来越多地配备了记忆,这些记忆存储了经验并可重复使用,以提高任务解决性能。最近的自我进化系统根据交互结果更新记忆,但大多数现有进化管道都是为静态训练/测试分割开发的,仅通过折叠静态基准进行近似在线学习,使其在真正的分布偏移和连续反馈下变得脆弱。我们引入了Live-Evo,一个在线自我进化记忆系统,它从不断涌入的数据流中学习。Live-Evo通过经验银行和元指导银行解耦

英文摘要:

Large language model (LLM) agents are increasingly equipped with memory, which are stored experience and reusable guidance that can improve task-solving performance. Recent \emph{self-evolving} systems update memory based on interaction outcomes, but most existing evolution pipelines are developed for static train/test splits and only approximate online learning by folding static benchmarks, making them brittle under true distribution shift and continuous feedback. We introduce \textsc{Live-Evo}, an online self-evolving memory system that learns from a stream of incoming data over time. \textsc{Live-Evo} decouples \emph{what happened} from \emph{how to use it} via an Experience Bank and a Meta-Guideline Bank, compiling task-adaptive guidelines from retrieved experiences for each task. To manage memory online, \textsc{Live-Evo} maintains experience weights and updates them from feedback: experiences that consistently help are reinforced and retrieved more often, while misleading or stale experiences are down-weighted and gradually forgotten, analogous to reinforcement and decay in human memory. On the live \textit{Prophet Arena} benchmark over a 10-week horizon, \textsc{Live-Evo} improves Brier score by 20.8\% and increases market returns by 12.9\%, while also transferring to deep-research benchmarks with consistent gains over strong baselines. Our code is available at https://github.com/ag2ai/Live-Evo.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑