动态删减冗余智能体，提升大模型多智能体协作效率与性能
AgentDropout: Dynamic Agent Elimination for Token-Efficient and High-Performance LLM-Based Multi-Agent Collaboration
- 通过优化通信图邻接矩阵，动态识别并移除冗余智能体和通信
- 提示词消耗减少21.6%，完成词消耗减少18.4%，任务性能提升1.14
- 适用于追求高效低耗的多智能体系统，尤其适合资源受限场景
基于大语言模型的多智能体系统在协同问题求解中展现出巨大潜力，但仍面临通信效率低、任务表现不佳的问题，因此智能体通信拓扑的设计尤为关键。受高效团队角色动态调整管理理论启发，我们提出AgentDropout，通过优化通信图的邻接矩阵，动态识别并消除不同通信轮次中的冗余智能体与通信路径，从而提升令牌效率与任务性能。相比现有先进方法，AgentDropout平均降低21.6%的提示词消耗与18.4%的完成词消耗，同时在任务上取得1.14的性能提升。扩展实验表明，该方法具备显著的领域迁移能力与结构鲁棒性，验证了其可靠性与有效性。代码已开源：https://github.com/wangzx1219/AgentDropout。
原文摘要 · Abstract (English)
Multi-agent systems (MAS) based on large language models (LLMs) have demonstrated significant potential in collaborative problem-solving. However, they still face substantial challenges of low communication efficiency and suboptimal task performance, making the careful design of the agents' communication topologies particularly important. Inspired by the management theory that roles in an efficient team are often dynamically adjusted, we propose AgentDropout, which identifies redundant agents and communication across different communication rounds by optimizing the adjacency matrices of the communication graphs and eliminates them to enhance both token efficiency and task performance. Compared to state-of-the-art methods, AgentDropout achieves an average reduction of 21.6% in prompt token consumption and 18.4% in completion token consumption, along with a performance improvement of 1.14 on the tasks. Furthermore, the extended experiments demonstrate that AgentDropout achieves notable domain transferability and structure robustness, revealing its reliability and effectiveness. We release our code at https://github.com/wangzx1219/AgentDropout.
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。