使用与弃用：面向大语言模型智能体记忆与学习的意图结构化经验整合
Use and Disuse: Intent-Structured Experience Consolidation for Memory and Learning in LLM Agents
- Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所）
- School of Cyber Security, University of Chinese Academy of Sciences（中国科学院大学网络空间安全学院）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
针对大语言模型智能体将连续经验转化为可复用知识的挑战，提出Hippocam架构，通过意图结构化经验整合实现无需参数更新的自主学习与能力提升。
AI中文摘要：
大语言模型智能体从单任务执行向长期自主运行的演进，凸显了将连续经验转化为可复用知识的关键挑战。为解决这一问题，我们提出Hippocam，一种分层记忆与持续学习架构。Hippocam借鉴人类记忆的两个特征：认知过程选择性保留与当前目标相关的信息，长期记忆则通过重复整合逐步形成。据此，Hippocam将智能体的持续工作构建为嵌套意图结构：活跃上下文始终以当前意图为中心，已完成意图则整合为后续工作所需的任务相关结果与状态，而非保留全部工作细节；同时，递归前缀整合机制会反复整合早期历史，使长期未使用的经验愈发抽象，同时保留原始交互，让智能体可通过层级结构逐步恢复更细粒度的细节，并在获取足够信息后停止。关键在于，过往经验被召回并重新整合至活跃工作时，会与新经验一同经历后续整合，从而得到强化、补充与更新。通过这种“使用与弃用”的记忆动态，Hippocam在单一持续演进的经验过程中连接了工作上下文、长期记忆、知识积累与技能学习，使智能体无需参数更新即可通过自身经验学习并提升能力。
英文摘要：
The evolution of Large Language Model agents from single-task execution to long-term autonomous operation highlights the critical challenge of transforming continuous experiences into reusable knowledge. To address this, we propose Hippocam, a hierarchical memory and continual learning architecture. Hippocam draws inspiration from two characteristics of human memory: cognitive processes selectively maintain information relevant to current goals, while long-term memories form gradually through repeated consolidation. Accordingly, Hippocam structures an agent's ongoing work as nested intents. The active context remains centered on the current intent, while completed intents are consolidated into the task-relevant outcomes and state needed for subsequent work, rather than carrying forward their full working details. Concurrently, a recursive prefix consolidation mechanism repeatedly consolidates earlier history, causing long-unused experiences to become increasingly abstract. Original interactions are preserved, allowing the agent to progressively recover finer-grained details through the hierarchy and stop once sufficient information is available. Crucially, when past experiences are recalled and reintegrated into active work, they undergo subsequent consolidation alongside new experiences, thereby being reinforced, supplemented, and updated. Through this memory dynamic of use and disuse, Hippocam connects working context, long-term memory, knowledge accumulation, and skill learning within a single continuously evolving experiential process. This enables agents to learn and evolve capabilities through their own experiences without parameter updates.
