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 2602.07885cs.AIcs.LG
收藏

MemFly: 通过信息瓶颈实现飞地内存优化

MemCoRe: Recovering Evidence from Progressively Compressed Factual Knowledge for Agent Memory

The Hong Kong University of Science(香港科学与技术大学);Nanjing University of Science(南京理工大学)

Zhenyuan Zhang, Xianzhang Jia, Zhiqin Yang, Zhenbo Song, Wei Xue, Sirui Han, Yike Guo

AI总结:

MemFly通过信息瓶颈原理实现LLM的飞地内存优化,采用梯度自由优化器和混合检索机制提升内存效率和多跳查询能力。

摘要:

长期记忆使大语言模型代理能够通过历史交互解决复杂任务。然而,现有框架在高效压缩冗余信息与保持下游任务精确检索之间面临根本性矛盾。为解决这一问题,我们提出MemFly,一个基于信息瓶颈原理的框架,为LLMs实现飞地内存进化。我们的方法通过梯度自由优化器最小化压缩熵同时最大化相关性熵,构建高效的分层内存结构。为充分利用MemFly,我们开发了一种混合检索机制,无缝整合语义、符号和拓扑路径,通过迭代细化处理复杂多跳查询。全面实验表明,MemFly在内存一致性、响应保真度和准确性方面显著优于最先进的基线。

英文摘要:

Memory systems enable LLM agents to consolidate and retrieve relevant evidence from the factual knowledge accumulated through growing interaction histories for downstream reasoning. Existing approaches have explored diverse strategies for organizing and compressing these histories. However, balancing compression with retrieval effectiveness remains challenging: retaining too much content can cause relevant evidence to be obscured by redundant entries, while discarding too aggressively may remove content that later proves relevant. This amounts to a tradeoff between compressing redundancy and preserving enough structure to retrieve target evidence, as formalized by the information bottleneck. To this end, we propose MemCoRe, which organizes memory as a compression hierarchy where each level compresses redundancy further while retaining the structure needed for retrieval at that level. In this hierarchy, evidence is progressively compressed from detailed records through extracted keywords to topic groups. This enables retrieval to locate target evidence by searching across levels of the hierarchy. Comprehensive experiments demonstrate that MemCoRe outperforms existing state-of-the-art baselines.

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。

↑