用图神经网络动态设计智能体通信拓扑，提升效率与鲁棒性。
G-Designer: Architecting Multi-agent Communication Topologies via Graph Neural Networks
- 基于变分图自编码器构建任务感知的智能体通信网络。
- 在MMLU上达84.50%准确率，HumanEval pass@1达89.90%。
- 能根据任务难度自动优化通信结构，减少95.33%通信开销。
大型语言模型（LLM）驱动的智能体系统表明，协同智能可显著超越单个智能体的能力，关键在于精心设计的智能体间通信拓扑。尽管已有多种高性能设计，但实践者在选择适合特定任务的通信方案时仍面临困惑：如何在避免冗余通信开销的同时确保高质量解？为此，我们提出G-Designer，一种自适应、高效且鲁棒的多智能体部署方案，可动态构建任务感知的定制化通信拓扑。G-Designer将多智能体系统建模为多智能体网络，利用变分图自编码器对节点（智能体）及任务相关的虚拟节点进行编码，并解码出任务适配且高性能的通信拓扑。在六个基准上的大量实验表明，G-Designer具有：(1) 高性能，在MMLU上达到84.50%准确率，在HumanEval上pass@1达89.90%；(2) 任务自适应性，针对任务难度定制通信协议，使HumanEval上通信令牌消耗降低高达95.33%；(3) 对抗鲁棒性，在对抗攻击下仅导致0.3%准确率下降。
原文摘要 · Abstract (English)
Recent advancements in large language model (LLM)-based agents have demonstrated that collective intelligence can significantly surpass the capabilities of individual agents, primarily due to well-crafted inter-agent communication topologies. Despite the diverse and high-performing designs available, practitioners often face confusion when selecting the most effective pipeline for their specific task: \textit{Which topology is the best choice for my task, avoiding unnecessary communication token overhead while ensuring high-quality solution?} In response to this dilemma, we introduce G-Designer, an adaptive, efficient, and robust solution for multi-agent deployment, which dynamically designs task-aware, customized communication topologies. Specifically, G-Designer models the multi-agent system as a multi-agent network, leveraging a variational graph auto-encoder to encode both the nodes (agents) and a task-specific virtual node, and decodes a task-adaptive and high-performing communication topology. Extensive experiments on six benchmarks showcase that G-Designer is: \textbf{(1) high-performing}, achieving superior results on MMLU with accuracy at $84.50\%$ and on HumanEval with pass@1 at $89.90\%$; \textbf{(2) task-adaptive}, architecting communication protocols tailored to task difficulty, reducing token consumption by up to $95.33\%$ on HumanEval; and \textbf{(3) adversarially robust}, defending against agent adversarial attacks with merely $0.3\%$ accuracy drop.
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。