@inproceedings{kaesberg-etal-2025-voting,
    title = "Voting or Consensus? Decision-Making in Multi-Agent Debate",
    author = "Kaesberg, Lars Benedikt  and
      Becker, Jonas  and
      Wahle, Jan Philip  and
      Ruas, Terry  and
      Gipp, Bela",
    editor = "Che, Wanxiang  and
      Nabende, Joyce  and
      Shutova, Ekaterina  and
      Pilehvar, Mohammad Taher",
    booktitle = "Findings of the Association for Computational Linguistics: ACL 2025",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/mtsummit-25-ingestion/2025.findings-acl.606/",
    doi = "10.18653/v1/2025.findings-acl.606",
    pages = "11640--11671",
    ISBN = "979-8-89176-256-5",
    abstract = "Much of the success of multi-agent debates depends on carefully choosing the right parameters. The decision-making protocol stands out as it can highly impact final model answers, depending on how decisions are reached. Systematic comparison of decision protocols is difficult because many studies alter multiple discussion parameters beyond the protocol. So far, it has been largely unknown how decision-making influences different tasks. This work systematically evaluates the impact of seven decision protocols (e.g., majority voting, unanimity consensus). We change only one variable at a time - the decision protocol - to analyze how different methods affect the collaboration between agents and measure differences in knowledge and reasoning tasks. Our results show that voting protocols improve performance by 13.2{\%} in reasoning tasks and consensus protocols by 2.8{\%} in knowledge tasks compared to other decision protocols. Increasing the number of agents improves performance, while more discussion rounds before voting reduce it. To improve decision-making by increasing answer diversity, we propose two new methods, All-Agents Drafting (AAD) and Collective Improvement (CI). Our methods improve task performance by up to 3.3{\%} with AAD and up to 7.4{\%} with CI. This work demonstrates the importance of decision-making in multi-agent debates beyond scaling."
}