DynaDebate: Breaking Homogeneity in Multi-Agent Debate with Dynamic Path Generation

2026-01-09

arXiv.org

AI Summary

This work addresses a critical limitation in existing multi-agent debate frameworks: the lack of guided initialization often leads to homogeneous reasoning paths, which can result in collective errors and reduce debates to mere majority voting. To overcome this, the paper proposes a novel multi-agent debate framework that enhances reasoning diversity through a dynamic path generation and allocation mechanism. It further introduces a process-oriented, stepwise logical critique mechanism that prioritizes the correctness of reasoning over outcome-based voting, and incorporates a trigger-based external tool verification module to resolve deadlocks. Empirical evaluations demonstrate that the proposed method significantly outperforms state-of-the-art approaches across multiple benchmarks, substantially improving both accuracy and robustness in solving complex problems.

Technology Category

• Multiagent Systems: Agreement, Argumentation & Negotiation
• Knowledge Representation and Reasoning: Argumentation
• Reasoning under Uncertainty: Other Foundations of Reasoning under Uncertainty

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

Recent years have witnessed the rapid development of Large Language Model-based Multi-Agent Systems (MAS), which excel at collaborative decision-making and complex problem-solving. Recently, researchers have further investigated Multi-Agent Debate (MAD) frameworks, which enhance the reasoning and collaboration capabilities of MAS through information exchange and debate among multiple agents. However, existing approaches often rely on unguided initialization, causing agents to adopt identical reasoning paths that lead to the same errors. As a result, effective debate among agents is hindered, and the final outcome frequently degenerates into simple majority voting. To solve the above problem, in this paper, we introduce Dynamic Multi-Agent Debate (DynaDebate), which enhances the effectiveness of multi-agent debate through three key mechanisms: (1) Dynamic Path Generation and Allocation, which employs a dedicated Path Generation Agent to generate diverse and logical solution paths with adaptive redundancy; (2) Process-Centric Debate, which shifts the focus from surface-level outcome voting to rigorous step-by-step logic critique to ensure process correctness; (3) A Trigger-Based Verification Agent, which is activated upon disagreement and uses external tools to objectively resolve deadlocks. Extensive experiments demonstrate that DynaDebate achieves superior performance across various benchmarks, surpassing existing state-of-the-art MAD methods.

Problem

• Multi-Agent Debate
• Reasoning Homogeneity
• Path Diversity
• Collaborative Reasoning
• LLM-based MAS

Innovation

• Dynamic Path Generation
• Multi-Agent Debate
• Process-Centric Reasoning
• Trigger-Based Verification
• Reasoning Diversity