MemSkill：為自進化代理學習與演化記憶技能

摘要

當前大多數大型語言模型（LLM）智能體記憶系統依賴於少量靜態、人工設計的記憶提取操作。這些固定流程將人類對存儲內容和記憶修訂方式的先驗知識硬編碼其中，導致其在多樣化互動模式下缺乏靈活性，且在處理長歷史記錄時效率低下。為此，我們提出MemSkill，將這些操作重新定義為可學習、可演進的記憶技能——即從互動軌跡中提取、整合和刪減信息的結構化可複用例程。受智能體技能設計理念啟發，MemSkill採用學習選擇相關技能的控制器，並搭配基於LLM的執行器來生成技能引導的記憶。除了學習技能選擇策略，MemSkill還引入設計器模組，定期覆核因所選技能導致記憶錯誤或不完整的困難案例，並通過改進現有技能或提出新技能來演進技能集合。由此，MemSkill形成一個閉環流程，同步優化技能選擇策略與技能集合本身。在LoCoMo、LongMemEval、HotpotQA和ALFWorld上的實驗表明，MemSkill在任務表現上優於強基線模型，且在不同場景中展現良好泛化能力。進一步分析揭示了技能的演進機制，為實現更自適應、自演進的LLM智能體記憶管理提供了重要洞見。

English

Most Large Language Model (LLM) agent memory systems rely on a small set of static, hand-designed operations for extracting memory. These fixed procedures hard-code human priors about what to store and how to revise memory, making them rigid under diverse interaction patterns and inefficient on long histories. To this end, we present MemSkill, which reframes these operations as learnable and evolvable memory skills, structured and reusable routines for extracting, consolidating, and pruning information from interaction traces. Inspired by the design philosophy of agent skills, MemSkill employs a controller that learns to select a small set of relevant skills, paired with an LLM-based executor that produces skill-guided memories. Beyond learning skill selection, MemSkill introduces a designer that periodically reviews hard cases where selected skills yield incorrect or incomplete memories, and evolves the skill set by proposing refinements and new skills. Together, MemSkill forms a closed-loop procedure that improves both the skill-selection policy and the skill set itself. Experiments on LoCoMo, LongMemEval, HotpotQA, and ALFWorld demonstrate that MemSkill improves task performance over strong baselines and generalizes well across settings. Further analyses shed light on how skills evolve, offering insights toward more adaptive, self-evolving memory management for LLM agents.

MemSkill：為自進化代理學習與演化記憶技能

MemSkill: Learning and Evolving Memory Skills for Self-Evolving Agents

摘要

Support