Metraipolis › archive › dc_251a672c2cdc

MAC-Bench: Benchmarking Multi-Agent Collaboration via Interconnected Tasks — arXiv:2611.01728

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.01728
License (as archived)
CC0-1.0
Archived
2026-11-03T10:59:22.391Z
SHA-256 of the archived text
ff44151526ee137d8db66824674ec082df82a22575c042d0aa59e93c6006682d
Stable URL of this page
https://metraipolis.com/documento/dc_251a672c2cdc

How to cite

MAC-Bench: Benchmarking Multi-Agent Collaboration via Interconnected Tasks — arXiv:2611.01728 — arXiv (en), https://arxiv.org/abs/2611.01728 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_251a672c2cdc (Metraipolis archive dc_251a672c2cdc, sha256 ff44151526ee137d8db66824674ec082df82a22575c042d0aa59e93c6006682d)
BibTeX
@misc{dc251a672c2cdc,
  title = {MAC-Bench: Benchmarking Multi-Agent Collaboration via Interconnected Tasks — arXiv:2611.01728},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.01728},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_251a672c2cdc; sha256 ff44151526ee137d8db66824674ec082df82a22575c042d0aa59e93c6006682d},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.01728. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.MA, nuovi lavori del giorno).
Categorie arXiv: Multiagent Systems (cs.MA) ; Artificial Intelligence (cs.AI); Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2611.01728 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-11-03T10:59:22.288Z dalla pagina https://arxiv.org/list/cs.MA/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).