arXiv 研究：LLM 多智能体团队换人时“角色可互换，但历史不可替代”
Interchangeable in Role, Not in History: Replacing Members of Formed LLM Teams
AI 导读
arXiv 一项研究测试多智能体 LLM 团队中的成员替换问题，发现带着另一团队笔记本的同角色新成员虽优于无笔记本者，但在协作烹饪、野火响应和医疗问答任务中均不及原团队成员，且团队每单位进度需更多消息。
正文 · 原文
Abstract:Multiagent LLM systems often treat a role as a slot: when a member is replaced, any agent competent at the role is expected to fill it. We test this view on teams whose members keep short written notebooks. A one-seat swap replays a formed, frozen team with its own member, with a same-role newcomer carrying another team's notebook for that role, or with a newcomer carrying none. In cooperative cooking, wildfire response and medical question answering, the experienced newcomer, averaged over seats, outscores the one without a notebook in every setting, so the usual comparison would approve it. Against the original team, the same replacement falls short in every setting, and the team spends more messages per unit of progress. On the hardest cooking level, the shortfall appears only after the team has worked together, persists across model families and decoding temperatures, and narrows by two thirds with added planning-only members. Because the team's history is written down, we can take it apart. In the default configuration on that level, notebooks from the same donor teams leave a newcomer that leads, holding the recipe, worse off than no notebook and one that follows better off. The notebook lines about the partner reproduce this whole difference between the seats. Whether an agent can replace a teammate depends on the seat and the team it enters.
| Subjects: | Artificial Intelligence (cs.AI); Multiagent Systems (cs.MA) |
| Cite as: | arXiv:2609.05279 [cs.AI] |
| (or arXiv:2609.05279v2 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2609.05279 arXiv-issued DOI via DataCite |
Submission history
From: Jianxin Gao [view email]
[v1]
Fri, 4 Sep 2026 15:32:20 UTC (49 KB)
[v2]
Fri, 23 Oct 2026 15:18:48 UTC (1,132 KB)
来源：arXiv cs.AI · arxiv.org