动态选择协作图结构，让大模型多智能体系统更灵活高效。
DynaSwarm: Dynamically Graph Structure Selection for LLM-based Multi-agent System
- 用强化学习动态优化智能体间的连接关系。
- 在问答、数学推理等任务上超越现有单/多智能体基线。
- 适合需要自适应协作的复杂任务场景。
当前基于大模型的多智能体系统（MAS）普遍依赖人工设计且固定的协作图结构，限制了系统的适应性和性能。为此，我们提出DynaSwarm，一个通过两项创新提升大模型多智能体系统性能的动态框架：（1）采用演员-评论家强化学习（A2C）机制，实现对图结构的优化，在稳定性上优于先前的强化学习方法；（2）引入动态图选择器，通过参数高效的LLM微调，为每个输入样本自适应地选择最优图结构。该方法摒弃了固定统一的架构，转而利用样本特异性，将查询动态路由至专精的智能体网络。此外，我们还通过微调示范检索器，充分挖掘上下文学习（ICL）潜力。在问答、数学推理和编程任务上的大量实验表明，DynaSwarm在多个大模型主干上均持续优于现有的单智能体与多智能体基线。研究结果强调了在大模型多智能体系统中，基于样本感知的结构灵活性的重要性。
原文摘要 · Abstract (English)
Current multi-agent systems (MAS) frameworks often rely on manually designed and static collaboration graph structures, limiting adaptability and performance. To address these limitations, we propose DynaSwarm, a dynamic framework that enhances LLM-based MAS through two key innovations: (1) an actor-critic reinforcement learning (A2C) mechanism to optimize graph structures with improved stability over prior RL methods, and (2) a dynamic graph selector that adaptively chooses the optimal graph structure for each input sample via parameter-efficient LLM fine-tuning. DynaSwarm eliminates the need for rigid, one-fits-all graph architectures, instead leveraging sample-specific idiosyncrasies to dynamically route queries through specialized agent networks. (c) We propose to fine-tune the demonstration retriever to fully exploit the power of in-context learning (ICL). Extensive experiments on question answering, mathematical reasoning, and coding tasks demonstrate that DynaSwarm consistently outperforms state-of-the-art single-agent and MAS baselines across multiple LLM backbones. Our findings highlight the importance of sample-aware structural flexibility in LLM MAS designs.
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。