arXiv cs.CL· To Eun Kim, Xuhong He, Dishank Jain, Ambuj Agrawal, Negar Arabzadeh, Fernando Diaz·· 2 天前AI 评分37
多智能体交互记忆（MATM）：跨智能体轨迹共享与检索框架
Multi-Agent Transactive Memory
AI 导读
研究者提出多智能体交互记忆（MATM）框架，让生产者智能体将轨迹贡献到共享仓库，消费者智能体检索复用，实现群体级经验存储与检索。在 ALFWorld 和 WebArena 长流程交互环境中，从 MATM 检索可提升下游任务表现并减少交互步数，且无需协调或联合训练。
正文 · 原文
Abstract:Decentralized deployment of LLM agents with diverse capabilities motivates infrastructure for knowledge sharing across heterogeneous agent populations. Just as search engines index human-generated artifacts for human problem solving, retrieval systems can organize agent-generated artifacts for reuse across agents, extending retrieval-augmented generation from human-authored documents to agent-generated ones. Agent trajectories in particular encode reusable procedural knowledge, yet are typically discarded after a single use or retained only by the producing agent, forcing newly instantiated agents to rediscover existing solutions. We propose Multi-Agent Transactive Memory (MATM), a framework for population-level storage and retrieval of agent trajectories, where producer agents contribute trajectories to a shared repository and consumer agents retrieve them to improve task execution. In interactive environments with long, procedurally rich trajectories (ALFWorld and WebArena), retrieving from MATM improves downstream task performance and reduces interaction steps without coordination or joint training, positioning MATM as a design pattern for population-level experience sharing in open agent ecosystems.
| Subjects: | Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Information Retrieval (cs.IR) |
| Cite as: | arXiv:2606.19911 [cs.AI] |
| (or arXiv:2606.19911v2 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2606.19911 arXiv-issued DOI via DataCite |
Submission history
From: To Eun Kim [view email]
[v1]
Thu, 18 Jun 2026 08:04:59 UTC (388 KB)
[v2]
Thu, 15 Oct 2026 01:05:52 UTC (393 KB)
来源：arXiv cs.CL · arxiv.org