让大模型智能记忆任务经验，自动优化长期记忆。
AdMem: Advanced Memory for Task-solving Agents
- 三重记忆融合：语义、事件、流程记忆分层存储
- 多智能体协作实现自动记忆生成与奖励标注
- 基于奖励动态合并/删除记忆，支持持续进化
大型语言模型（LLMs）在工具使用代理中展现潜力，但在需要长期记忆、组织和复用知识的复杂任务中仍受限。现有记忆方法多聚焦于事实存储，近期的程序性记忆虽提升任务复用能力，却常陷入重复成功案例，忽略失败情形且难以在线扩展。本文提出一种统一的自动化记忆框架，采用双层设计整合语义、情景和程序性记忆，结合短期与长期存储。通过包含执行者、记忆体和评判者三个智能体的架构，实现自动记忆生成、奖励标注与自适应检索。长期记忆通过奖励驱动评估、合并与修剪机制管理，保障可扩展性与持续改进。在多种环境中的实验表明，相比现有基线，该方法显著提升了长周期多轮任务的鲁棒性与成功率。本工作强调了全面、自适应记忆对推进基于LLM的智能体的重要性。
原文摘要 · Abstract (English)
Large Language Models (LLMs) show promise as tool-using agents but remain limited in long-horizon tasks that require remembering, organizing, and reusing knowledge. Prior memory approaches aim to resolve the situation, but mainly focus on storing factual information. Recent work on procedural memory improves task reuse, yet often reduces to replaying past successes without addressing failure cases or online scalability. We introduce a unified and automatic memory framework that integrates semantic, episodic, and procedural memory in a bi-level design combining short-term and long-term stores. A multi-agent architecture with actor, memory, and critic agents enables automatic memory generation, reward annotation, and adaptive retrieval. Long-term memory is managed through reward-based evaluation, merging, and pruning, ensuring scalability and continual improvement. Experiments across various environments show that our approach improves robustness and success on long multi-turn tasks compared to existing baselines. This work highlights the importance of comprehensive, adaptive memory for advancing LLM-based agents.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。