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.

翻译：基于大语言模型（LLM）的智能体近期进展表明，通过精心设计的智能体间通信拓扑，集体智能能够显著超越单个智能体的能力。尽管现有设计方案多样且性能优异，实践者在为其特定任务选择最有效流程时仍常感困惑：\textit{对于我的任务，哪种拓扑是最佳选择，既能避免不必要的通信令牌开销，又能确保高质量解决方案？} 针对此困境，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，能够动态设计任务感知的定制化通信拓扑。具体而言，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）和任务特定虚拟节点进行编码，并解码出适应任务且高性能的通信拓扑。在六个基准测试上的大量实验表明，G-Designer具有以下特性：\textbf{（1）高性能}，在MMLU上准确率达到$84.50\%$，在HumanEval上pass@1达到$89.90\%$；\textbf{（2）任务自适应性}，能根据任务难度定制通信协议，在HumanEval上最高可减少$95.33\%$的令牌消耗；\textbf{（3）对抗鲁棒性}，在遭受智能体对抗攻击时仅出现$0.3\%$的准确率下降。