用动态调度器让多个大模型协作解题，效率更高更灵活。
Multi-Agent Collaboration via Evolving Orchestration
- 中心化调度器实时指挥多个大模型，按需调整协作顺序。
- 在封闭与开放任务中表现更优，计算开销更低。
- 能自发形成紧凑循环推理结构，适合复杂任务场景。
大型语言模型（LLMs）在多种下游任务中表现优异，但其单体架构限制了复杂问题求解中的可扩展性与效率。尽管已有研究探索多代理协作，但多数方法依赖静态组织结构，在任务复杂度和代理数量增加时难以适应，导致协调开销大、效率低。为此，我们提出一种类傀儡师的范式，由中央调度器（“傀儡师”）根据任务状态动态指挥多个代理（“木偶”）。该调度器通过强化学习训练，可自适应地排序和优先级分配代理，实现灵活且可演化的集体推理。在封闭域与开放域场景的实验表明，该方法在性能上优于现有方案，同时计算成本更低。分析进一步揭示，性能提升主要源于调度器演化中涌现出更紧凑、循环式的推理结构。代码已开源：https://github.com/OpenBMB/ChatDev/tree/puppeteer。
原文摘要 · Abstract (English)
Large language models (LLMs) have achieved remarkable results across diverse downstream tasks, but their monolithic nature restricts scalability and efficiency in complex problem-solving. While recent research explores multi-agent collaboration among LLMs, most approaches rely on static organizational structures that struggle to adapt as task complexity and agent numbers grow, resulting in coordination overhead and inefficiencies. To this end, we propose a puppeteer-style paradigm for LLM-based multi-agent collaboration, where a centralized orchestrator ("puppeteer") dynamically directs agents ("puppets") in response to evolving task states. This orchestrator is trained via reinforcement learning to adaptively sequence and prioritize agents, enabling flexible and evolvable collective reasoning. Experiments on closed- and open-domain scenarios show that this method achieves superior performance with reduced computational costs. Analyses further reveal that the key improvements consistently stem from the emergence of more compact, cyclic reasoning structures under the orchestrator's evolution. Our code is available at https://github.com/OpenBMB/ChatDev/tree/puppeteer.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。