cs.MANov 1, 2026

MAC-Bench: Benchmarking Multi-Agent Collaboration via Interconnected Tasks

Authors: Zerui Chen, Qinggang Zhang, Qichuan Liu, Zhishang Xiang, Zhimin Wei, Yunbo Tang, Zhuo Li, Jinsong Su, 

Organizations: Xiamen University · Jilin University · ByteDance

Abstract

Large language model (LLM)-based multi-agent systems (MAS) tackle challenging tasks by dividing work among agents and coordinating their contributions toward shared objectives. Evaluating these systems therefore requires benchmarks that assess not only task-solving performance but also the ability to handle interdependent work. However, existing benchmarks often emphasize task difficulty without substantial collaboration requirements or evaluate only a limited range of predefined collaboration patterns. In this paper, we introduce MAC-Bench, a comprehensive benchmark for evaluating multi-agent collaboration through interconnected tasks. Rather than imposing predefined agent roles or communication protocols, MAC-Bench embeds collaboration requirements directly into task dependencies and shared-resource constraints. Specifically, we mine reusable collaboration structures from selected benchmark tasks at two levels. Local collaboration patterns capture recurring interactions among subtasks, while global task structures characterize how these interactions contribute to complete workflows. Through coarse-to-fine composition, these structures are recombined into task graphs combining different collaboration requirements. Tasks are instantiated in executable environments with automated verification of partial progress and complete task resolution.

Figures & tables

Appendix figures & tables31 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. MASBench: Benchmarking LLM-based Multi-Agent Collaboration under Partial Observability

    Oct 3, 2026Qizhi Chu, Zekai Yu, Sijie Wen +5Multi-Agent LLM SystemsMulti-Agent Collaboration

  2. MASTraceBench: Diagnosing Collaboration Gains through Proposal Trajectories in LLM-Based Multi-Agent Systems

    Sep 28, 2026Yapeng Li, Songze Li, Shuang Yu +4Multi-Agent LLM SystemsMulti-Agent Collaboration

  3. ForestBench: A Unified Graph Framework for Evaluating Multi-Agent Collaboration

    Aug 9, 2026Guo Chen, Ziwen Li, Reed Li +4Multi-Agent LLM SystemsAI Agent Evaluation