arXiv cs.MA· Congjia Tian, Yuhang Yao, Jiaming Cui·· 11 小时前AI 评分31
QueenBee：面向 LLM 多智能体系统通信拓扑设计的递归自我改进框架
QueenBee: A Recursively Self-Improving Harness for Communication Topology Design in LLM-Based Multi-Agent Systems
AI 导读
QueenBee 是一个经验引导的多智能体工作流进化框架，将工作流表示为可执行程序并生成时序通信 DAG，同时维护持久化结构记忆 SFT-Bank，存储执行诊断、设计假设、验证结果与历史程序。
正文 · 原文
Abstract:LLM-based multi-agent systems show great potential for complex tasks through role specialization and collaborative reasoning. However, existing automated workflow design methods primarily focus on one-off search and candidate optimization, lacking sustained accumulation and reuse of structural design experience to meet evolving coordination demands. We propose QueenBee, an experience-guided framework for multi-agent workflow evolution. QueenBee represents workflows as executable programs that generate temporal communication DAGs and maintains Structural Feedback and Transition Bank (SFT-Bank), a persistent structural memory of execution diagnoses, design hypotheses and validation outcomes, and historical programs. This accumulated experience guides subsequent workflow generation, validation, and optimization, enabling the co-evolution of collaboration programs and design experience. Experiments on Silo-Bench show that QueenBee outperforms fixed communication baselines across team sizes and achieves the highest mean task score among recent automated multi-agent workflow optimization methods. Ablation studies further show that SFT-Bank components provide complementary performance gains, while evolution dynamics reveal a consistently improving average trend in the quality of the best collaboration structures found across independent runs as structural experience accumulates.
| Subjects: | Multiagent Systems (cs.MA) |
| Cite as: | arXiv:2606.27492 [cs.MA] |
| (or arXiv:2606.27492v2 [cs.MA] for this version) | |
| https://doi.org/10.48550/arXiv.2606.27492 arXiv-issued DOI via DataCite |
Submission history
From: Jiaming Cui [view email]
[v1]
Thu, 25 Jun 2026 19:16:51 UTC (1,388 KB)
[v2]
Fri, 30 Oct 2026 04:12:34 UTC (1,768 KB)
来源：arXiv cs.MA · arxiv.org