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 2604.15877cs.AIcs.CLcs.MA
收藏

经验压缩光谱:在LLM代理中统一记忆、技能和规则

Experience Compression Spectrum: Unifying Memory, Skills, and Rules in LLM Agents

AWS Generative AI Innovation Center(AWS生成式AI创新中心);HSBC Holdings Plc., HSBC Technology Center, China(汇丰控股有限公司,汇丰技术中心,中国)

Xing Zhang, Guanghui Wang, Yanwei Cui, Wei Qiu, Ziyuan Li, Bing Zhu, Peiyang He

AI总结:

针对LLM代理长期多会话部署中经验管理效率问题,提出经验压缩光谱框架,统一记忆、技能和规则的压缩轴,解决压缩适应性和跨层级压缩缺失问题。

摘要:

随着LLM代理扩展至长周期、多会话部署,有效管理积累的经验成为关键瓶颈。代理记忆系统和技能发现均试图从交互痕迹中提取可重用知识,但1136篇论文的引用分析显示跨社区引用率低于1%。我们提出经验压缩光谱,将记忆、技能和规则定位为压缩轴上的点,通过5-20倍的事件记忆、50-500倍的程序性技能和1000倍以上的声明性规则压缩,直接减少上下文消耗、检索延迟和计算开销。将20余系统映射到此光谱显示,每个系统均处于固定预设压缩水平,无支持自适应跨层级压缩的系统,此为空缺对角线。进一步表明,专业化本身不足——两个社区独立解决共享子问题而不交换解决方案;评估方法紧密关联压缩水平;压缩程度越高,转移性增强但特异性降低;知识生命周期管理仍被忽视。我们阐述了可扩展、全光谱代理学习系统的开放问题和设计原则。

英文摘要:

As LLM agents scale to long-horizon, multi-session deployments, efficiently managing accumulated experience becomes a critical bottleneck. Agent memory systems and agent skill discovery both address this challenge, extracting reusable knowledge from interaction traces, yet a citation analysis of 1{,}136 references across 22 primary papers reveals a cross-community citation rate below 1\%. We propose the \emph{Experience Compression Spectrum}, a unifying framework that positions memory, skills, and rules as points along a single axis of increasing compression (5--20$\times$ for episodic memory, 50--500$\times$ for procedural skills, 1{,}000$\times$+ for declarative rules), directly reducing context consumption, retrieval latency, and compute overhead. Mapping 20+ systems onto this spectrum reveals that every system operates at a fixed, predetermined compression level: none supports adaptive cross-level compression, a gap we term the \emph{missing diagonal}. We further show that specialization alone is insufficient (both communities independently solve shared sub-problems without exchanging solutions), that evaluation methods are tightly coupled to compression levels, that transferability increases with compression at the cost of specificity, and that knowledge lifecycle management remains largely neglected. We articulate open problems and design principles for scalable, full-spectrum agent learning systems.

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。

↑