TensorX
返回文献探索

Paper · arXiv 2503.01935

MultiAgentBench: Evaluating the Collaboration and Competition of LLM agents

Kunlun Zhu, Hongyi Du, Zhaochen Hong, Xiaocheng Yang, Shuyi Guo, Zhe Wang, Zhenhailong Wang, Cheng Qian, Xiangru Tang, Heng Ji, Jiaxuan You

30 upvotesMarch 3, 2025arXiv 预印本
AI 摘要

A new benchmark evaluates LLM-based multi-agent systems in diverse scenarios, measuring task completion and quality of collaboration using coordination protocols and innovative strategies.

LLMsautonomous agentsMultiAgentBenchmulti-agent systemsmilestone-based key performance indicatorsstarchaintreegraph topologiesgroup discussioncognitive planning

Abstract

Large Language Models (LLMs) have shown remarkable capabilities as autonomous agents, yet existing benchmarks either focus on single-agent tasks or are confined to narrow domains, failing to capture the dynamics of multi-agent coordination and competition. In this paper, we introduce MultiAgentBench, a comprehensive benchmark designed to evaluate LLM-based multi-agent systems across diverse, interactive scenarios. Our framework measures not only task completion but also the quality of collaboration and competition using novel, milestone-based key performance indicators. Moreover, we evaluate various coordination protocols (including star, chain, tree, and graph topologies) and innovative strategies such as group discussion and cognitive planning. Notably, gpt-4o-mini reaches the average highest task score, graph structure performs the best among coordination protocols in the research scenario, and cognitive planning improves milestone achievement rates by 3%. Code and datasets are public available at https://github.com/MultiagentBench/MARBLE.

北京市昌平区探索星信息技术及软件开发工作室

京ICP备2026059466号
MultiAgentBench: Evaluating the Collaboration and Competition of LLM agents | TensorX