Voting or Consensus? Decision-Making in Multi-Agent Debate

• URL: http://arxiv.org/abs/2502.19130v3
• Date: Tue, 15 Jul 2025 08:12:34 GMT
• Title: Voting or Consensus? Decision-Making in Multi-Agent Debate
• Authors: Lars Benedikt Kaesberg, Jonas Becker, Jan Philip Wahle, Terry Ruas, Bela Gipp,
• Abstract summary: It has been largely unknown how decision-making influences different tasks.<n>Voting protocols improve performance by 13.2% in reasoning tasks and consensus protocols by 2.8% in knowledge tasks.<n>To improve decision-making by increasing answer diversity, we propose two new methods.
• Score: 6.655615220908708
• License: http://creativecommons.org/licenses/by-sa/4.0/
• 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.

Related papers

• Finding Common Ground: Using Large Language Models to Detect Agreement in Multi-Agent Decision Conferences [2.0543882079879996]
  Large Language Models (LLMs) have shown significant promise in simulating real-world scenarios.<n>We present a novel LLM-based multi-agent system designed to simulate group decision conferences.<n>Our results indicate that LLMs can reliably detect agreement even in dynamic and nuanced debates.
  arXiv  Detail & Related papers  (2025-07-11T09:31:10Z)
• PMAT: Optimizing Action Generation Order in Multi-Agent Reinforcement Learning [16.523999372817435]
  Action Generation with Plackett-Luce Sampling (AGPS) is a novel mechanism for agent decision order optimization.<n>We propose the Prioritized Multi-Agent Transformer (PMAT), a sequential decision-making MARL algorithm with decision order optimization.<n>Experiments on benchmarks including StarCraft II Multi-Agent Challenge, Google Research Football, and Multi-Agent MuJoCo show that PMAT outperforms state-of-the-art algorithms.
  arXiv  Detail & Related papers  (2025-02-23T08:30:14Z)
• RoundTable: Investigating Group Decision-Making Mechanism in Multi-Agent Collaboration [15.2119694237099]
  This study investigates the efficacy of Multi-Agent Systems in eliciting cross-agent communication and enhancing collective intelligence. By applying different voting rules in various environments, we find that moderate decision flexibility yields better outcomes.
  arXiv  Detail & Related papers  (2024-11-11T17:37:47Z)
• Mix Q-learning for Lane Changing: A Collaborative Decision-Making Method in Multi-Agent Deep Reinforcement Learning [8.455482816036689]
  This paper proposes a method named Mix Q-learning for Lane Changing(MQLC) At the collective level, our method coordinates the individual Q and global Q networks by utilizing global information. At the individual level, we integrated a deep learning-based intent recognition module into our observation and enhanced the decision network.
  arXiv  Detail & Related papers  (2024-06-14T06:44:19Z)
• ReConcile: Round-Table Conference Improves Reasoning via Consensus among Diverse LLMs [61.07130026622437]
  Large Language Models (LLMs) still struggle with natural language reasoning tasks. Motivated by the society of minds, we propose ReConcile. A multi-model multi-agent framework designed as a round table conference among diverse LLM agents.
  arXiv  Detail & Related papers  (2023-09-22T17:12:45Z)
• Decision-Oriented Dialogue for Human-AI Collaboration [62.367222979251444]
  We describe a class of tasks called decision-oriented dialogues, in which AI assistants such as large language models (LMs) must collaborate with one or more humans via natural language to help them make complex decisions. We formalize three domains in which users face everyday decisions: (1) choosing an assignment of reviewers to conference papers, (2) planning a multi-step itinerary in a city, and (3) negotiating travel plans for a group of friends. For each task, we build a dialogue environment where agents receive a reward based on the quality of the final decision they reach.
  arXiv  Detail & Related papers  (2023-05-31T17:50:02Z)
• ACE: Cooperative Multi-agent Q-learning with Bidirectional Action-Dependency [65.28061634546577]
  Multi-agent reinforcement learning (MARL) suffers from the non-stationarity problem. In this paper, we propose bidirectional action-dependent Q-learning (ACE) ACE outperforms the state-of-the-art algorithms on Google Research Football and StarCraft Multi-Agent Challenge.
  arXiv  Detail & Related papers  (2022-11-29T10:22:55Z)
• Policy Diagnosis via Measuring Role Diversity in Cooperative Multi-agent RL [107.58821842920393]
  We quantify the agent's behavior difference and build its relationship with the policy performance via bf Role Diversity We find that the error bound in MARL can be decomposed into three parts that have a strong relation to the role diversity. The decomposed factors can significantly impact policy optimization on three popular directions.
  arXiv  Detail & Related papers  (2022-06-01T04:58:52Z)
• Let's Agree to Agree: Targeting Consensus for Incomplete Preferences through Majority Dynamics [13.439086686599891]
  We focus on a process of majority dynamics where issues are addressed one at a time and undecided agents follow the opinion of the majority. We show that in the worst case, myopic adherence to the majority damages existing consensus; yet, simulation experiments indicate that the damage is often mild.
  arXiv  Detail & Related papers  (2022-04-28T10:47:21Z)
• Inverse Online Learning: Understanding Non-Stationary and Reactionary Policies [79.60322329952453]
  We show how to develop interpretable representations of how agents make decisions. By understanding the decision-making processes underlying a set of observed trajectories, we cast the policy inference problem as the inverse to this online learning problem. We introduce a practical algorithm for retrospectively estimating such perceived effects, alongside the process through which agents update them. Through application to the analysis of UNOS organ donation acceptance decisions, we demonstrate that our approach can bring valuable insights into the factors that govern decision processes and how they change over time.
  arXiv  Detail & Related papers  (2022-03-14T17:40:42Z)
• Efficient PAC Reinforcement Learning in Regular Decision Processes [99.02383154255833]
  We study reinforcement learning in regular decision processes. Our main contribution is to show that a near-optimal policy can be PAC-learned in time in a set of parameters.
  arXiv  Detail & Related papers  (2021-05-14T12:08:46Z)
• The Influence of Memory in Multi-Agent Consensus [0.8399688944263843]
  We propose a framework to study what we call emphmemory consensus protocol. We show that the employment of memory allows such processes to always converge, as well as, in some scenarios, such as cycles, converge faster. We provide a theoretical analysis of the probability of each option eventually winning such processes based on the initial opinions expressed by agents.
  arXiv  Detail & Related papers  (2021-05-10T20:59:35Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.