Large language model (LLM) agents have been shown effective on a wide range of tasks, and by ensembling multiple LLM agents, their performances could be further improved. Existing approaches employ a fixed set of agents to interact with each other in a static architecture, which limits their generalizability to various tasks and requires strong human prior in designing these agents. In this work, we propose to construct a strategic team of agents communicating in a dynamic interaction architecture based on the task query. Specifically, we build a framework named Dynamic LLM-Agent Network ($\textbf{DyLAN}$) for LLM-agent collaboration on complicated tasks like reasoning and code generation. DyLAN enables agents to interact for multiple rounds in a dynamic architecture with inference-time agent selection and an early-stopping mechanism to improve performance and efficiency. We further design an automatic agent team optimization algorithm based on an unsupervised metric termed $\textit{Agent Importance Score}$, enabling the selection of best agents based on the contribution each agent makes. Empirically, we demonstrate that DyLAN performs well in both reasoning and code generation tasks with reasonable computational cost. DyLAN achieves 13.0% and 13.3% improvement on MATH and HumanEval, respectively, compared to a single execution on GPT-35-turbo. On specific subjects of MMLU, agent team optimization in DyLAN increases accuracy by up to 25.0%.

基于任务查询构建动态交互结构的大型语言模型代理网络（DyLAN）在推理和代码生成任务中展现出良好性能，使用无监督度量的自动代理团队优化算法根据每个代理的贡献选择最佳代理，相较于GPT-35-turbo的单次执行，DyLAN在MATH和HumanEval任务上分别实现了13.0%和13.3%的改进，并在MMLU特定主题上提高了25.0%的准确率。

动态LLM-Agent网络：一种具有代理团队优化的LLM-agent协作框架