发现信息
- 作者:Yi Yu, Liuyi Yao, Yuexiang Xie, Qingquan Tan, Jiaqi Feng, Yaliang Li, Libing Wu
- 年份:2026
- 发表源:Proceedings of the conference - Association for Computational Linguistics. Meeting
- OpenAlex ID:https://openalex.org/W7166825402
- DOI:https://doi.org/10.18653/v1/2026.acl-long.981
- arXiv:待核验
- 检索主题:agent-memory
- OpenAlex 引用数快照:113(2026-11-12)
摘要线索
Large language model (LLM) agents face fundamental limitations in long-horizon reasoning due to finite context windows, making effective memory management critical.Existing methods typically handle long-term memory (LTM) and short-term memory (STM) as separate components, relying on heuristics or auxiliary controllers, which limits adaptability and end-to-end optimization.In this paper, we propose Agentic Memory (AgeMem), a unified framework that integrates LTM and STM management directly into the agent's policy.AgeMem exposes memory operations as tool-based actions, enabling the LLM agent to autonomously decide what and when to store, retrieve, update, summarize, or discard information.To train such unified behaviors, we propose a three-stage progressive reinforcement learning strategy and design a step-wise GRPO to address sparse and discontinuous rewards induced by memory operations.Experiments on five long-horizon benchmarks demonstrate that AgeMem consistently outperforms strong memory-augmented baselines across multiple LLM backbones, achieving improved task performance, higher-quality long-term memory, and more efficient context usage.
核验与筛选
- 当前状态:待筛选、去重和一手来源核验。
- OpenAlex 元数据和引用数只用于发现,不作为正式引文或质量判断。
- 记录正式版本、venue、方法细节、实验协议和局限后,才迁入稳定论文卡片。