# MemComposer：通过强化学习学习为LLM智能体组装记忆

> 原文链接：https://robotics.hellobike.com/papers/2026-10-15-2610-21091
> 频道：papers | 更新日期：2026-10-15 | 标签：arxiv, cs.RO
> 核心摘要：MemComposer通过强化学习按查询组装LLM智能体记忆，并在τ^2-bench三领域和两个冻结执行器上验证效果。

# MemComposer：通过强化学习学习为LLM智能体组装记忆

::: v-pre
> 原文链接：[MemComposer: Learning to Assemble Memories for LLM Agents via Reinforcement Learning](https://arxiv.org/abs/2610.21091)（arXiv 2610.21091 · 发布日期：2026-10-15）

**MemComposer: Learning to Assemble Memories for LLM Agents via Reinforcement Learning**

MemComposer通过强化学习按查询组装LLM智能体记忆，并在τ^2-bench三领域和两个冻结执行器上验证效果。

## 核心要点

- 动机：语义相似不保证记忆有用，性能取决于选择、数量与呈现顺序。
- 方法：联合考察当前查询与候选记忆，决定纳入哪些经验、数量和排序。
- 训练：ExPO基于GRPO，用完整智能体交互和任务成功反馈优化组装策略。
- 结果：在三领域两执行器上优于最强基线，平均记忆token用量分别降16.9%和4.9%。

**验证范围与局限**：验证限于三个τ^2-bench领域和两个冻结执行器，并包含未见领域、执行器与记忆库的迁移测试。

## 英文摘要 (Abstract)

Agent memory enables large language model (LLM) agents to reuse past experiences without updating their parameters. However, semantic similarity alone does not guarantee memory usefulness: downstream performance depends on how memories are selected and presented to the agent. We propose MemComposer, a memory composer that jointly examines the current query and retrieved candidates to decide which experiences to include, how many to select, and how to order them. We train the composer using Experience Policy Optimization (ExPO), a GRPO-based framework that evaluates assembled memory contexts through complete agent interactions and uses task-success feedback to optimize the assembly policy. Across three $τ^2$-bench domains with two frozen executors, MemComposer outperforms the strongest baseline for each executor while reducing average memory-token usage by 16.9% and 4.9%, respectively. The learned policy also transfers to unseen domains, executors, and memory banks, and benefits from memories generated by stronger models without further training. These results demonstrate the value of learning query-specific memory assembly using downstream task feedback.

作者：Yixuan Xie, Xueqiang Xu, Xinyi Fan, Xinxi Lyu, Tao Feng, Xing Fan, Chenlei Guo, Jie Hao, Shaowen Wang, Jiashuo Sun
:::

## 原始参考来源 (Sources)

- [arXiv 2610.21091：MemComposer: Learning to Assemble Memories for LLM Agents via Reinforcement Learning](https://arxiv.org/abs/2610.21091)