让大模型自己生成适时有用的记忆指引，比查数据库更智能。
Mem-$π$: Adaptive Memory through Learning When and What to Generate
- 用独立模型按需生成上下文相关的记忆指引
- 在网页导航任务中性能提升超30%
- 适合需要动态记忆的复杂智能体系统
我们提出 Mem-π，一种大语言模型智能体的自适应记忆框架，通过按需生成有用指引，而非从外部记忆库中检索。现有记忆增强型智能体通常依赖基于相似性的记忆检索，返回静态条目，常与当前上下文不符。Mem-π 使用一个独立的语言或视觉-语言模型（拥有自身参数），为复杂任务生成上下文相关的指引。该模型根据当前智能体状态，联合决定是否生成指引以及生成何种指引。我们采用决策-内容解耦的强化学习目标进行训练，使其在无益时选择不生成，否则输出简洁有效的指引。在涵盖网页导航、终端工具使用和文本驱动的具身交互等多种智能体基准测试中，Mem-π 持续优于基于检索和先前强化学习优化的记忆基线，在网页导航任务上相对提升超过30%。
原文摘要 · Abstract (English)
We present Mem-$π$, a framework for adaptive memory in large language model (LLM) agents, where useful guidance is generated on demand rather than retrieved from external memory stores. Existing memory-augmented agents typically rely on similarity-based retrieval from episodic memory banks or skill libraries, returning static entries that often misalign with the current context. In contrast, Mem-$π$ uses a dedicated language or vision-language model with its own parameters, separate from the downstream agent, to generate context-specific guidance for complex tasks. Conditioned on the current agent context, the model jointly decides when to produce guidance and what guidance to produce. We train it with a decision-content decoupled reinforcement learning (RL) objective, enabling it to abstain when generation would not help and otherwise produce concise, useful guidance. Across diverse agentic benchmarks spanning web navigation, terminal-based tool use, and text-based embodied interaction, Mem-$π$ consistently outperforms retrieval-based and prior RL-optimized memory baselines, achieving over 30% relative improvement on web navigation tasks.
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。