arXiv cs.AI· Wenbo Pan, Shujie Liu, Xiangyang Zhou, Xianlong Wang, Shiwei Zhang, Bingjing Xu, Wanlu Shi, Xiaohua Jia·· 4 小时前AI 评分51
M*：通过反思式代码演化自动搜索任务专属记忆框架
M$^\star$: Every Task Deserves Its Own Memory Harness
AI 导读
arXiv 论文提出 Mstar 方法，将大语言模型智能体的记忆框架表示为可执行的 Python 记忆程序，定义 Schema、Logic 和 Instruction 三个组件并通过反思式代码演化联合优化。
正文 · 原文
Abstract:Large language model agents rely on a memory harness to write, organize, retrieve, and use past experience. A harness that works for one task often fails on another, because conversations, embodied planning, and expert reasoning require different storage and retrieval behavior. To address this limitation, we introduce Mstar, a method that automatically discovers task-optimized memory programs through reflective code evolution. Specifically, Mstar operationalizes a memory harness as an executable Python memory program that defines the Schema, Logic, and Instruction, and optimizes these components jointly. We evaluate Mstar on four tasks covering conversation, embodied planning, and specialized reasoning. Our results demonstrate that Mstar improves performance over existing baselines across all evaluated tasks. Furthermore, the evolved memory programs exhibit structurally distinct processing mechanisms for each evaluated domain. These findings suggest that every task benefits from its own memory harness, and that memory-program search provides a concrete way to discover it.
| Comments: | NeurIPS 2026 (poster). Code: this https URL ; Live demo: this https URL |
| Subjects: | Programming Languages (cs.PL); Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Machine Learning (cs.LG) |
| Cite as: | arXiv:2604.11811 [cs.PL] |
| (or arXiv:2604.11811v3 [cs.PL] for this version) | |
| https://doi.org/10.48550/arXiv.2604.11811 arXiv-issued DOI via DataCite |
Submission history
From: Wenbo Pan [view email]
[v1]
Fri, 10 Apr 2026 03:22:26 UTC (761 KB)
[v2]
Sat, 23 May 2026 08:43:43 UTC (1,318 KB)
[v3]
Fri, 30 Oct 2026 06:13:10 UTC (1,308 KB)
来源：arXiv cs.AI · arxiv.org