Recent advancements in large language model (LLM)-powered agents have shown that collective intelligence can significantly outperform individual capabilities, largely attributed to the meticulously designed inter-agent communication topologies. Though impressive in performance, existing multi-agent pipelines inherently introduce substantial token overhead, as well as increased economic costs, which pose challenges for their large-scale deployments. In response to this challenge, we propose an economical, simple, and robust multi-agent communication framework, termed $\texttt{AgentPrune}$, which can seamlessly integrate into mainstream multi-agent systems and prunes redundant or even malicious communication messages. Technically, $\texttt{AgentPrune}$ is the first to identify and formally define the \textit{communication redundancy} issue present in current LLM-based multi-agent pipelines, and efficiently performs one-shot pruning on the spatial-temporal message-passing graph, yielding a token-economic and high-performing communication topology. Extensive experiments across six benchmarks demonstrate that $\texttt{AgentPrune}$ \textbf{(I)} achieves comparable results as state-of-the-art topologies at merely $\$5.6$ cost compared to their $\$43.7$, \textbf{(II)} integrates seamlessly into existing multi-agent frameworks with $28.1\%\sim72.8\%\downarrow$ token reduction, and \textbf{(III)} successfully defend against two types of agent-based adversarial attacks with $3.5\%\sim10.8\%\uparrow$ performance boost.

翻译：近期，基于大语言模型（LLM）的智能体研究进展表明，集体智能能够显著超越个体能力，这很大程度上归功于精心设计的智能体间通信拓扑结构。尽管现有多智能体管道在性能上表现优异，但其本质上引入了大量的令牌开销以及随之增加的经济成本，这对其大规模部署构成了挑战。为应对这一挑战，我们提出了一种经济、简单且鲁棒的多智能体通信框架，称为 $\texttt{AgentPrune}$。该框架能够无缝集成到主流多智能体系统中，并对冗余甚至恶意的通信消息进行剪枝。从技术上讲，$\texttt{AgentPrune}$ 首次识别并形式化定义了当前基于LLM的多智能体管道中存在的 \textit{通信冗余} 问题，并在时空消息传递图上高效执行一次性剪枝，从而生成一个令牌经济且高性能的通信拓扑。在六个基准测试上的大量实验表明，$\texttt{AgentPrune}$ \textbf{(I)} 仅需 $\$5.6$ 的成本（相比现有最优拓扑的 $\$43.7$）即可取得与之相当的结果，\textbf{(II)} 能够无缝集成到现有多智能体框架中，实现 $28.1\%\sim72.8\%\downarrow$ 的令牌削减，以及 \textbf{(III)} 成功抵御两类基于智能体的对抗攻击，并带来 $3.5\%\sim10.8\%\uparrow$ 的性能提升。