iMAD: Intelligent Multi-Agent Debate for Efficient and Accurate LLM Inference

• URL: http://arxiv.org/abs/2511.11306v1
• Date: Fri, 14 Nov 2025 13:50:51 GMT
• Title: iMAD: Intelligent Multi-Agent Debate for Efficient and Accurate LLM Inference
• Authors: Wei Fan, JinYi Yoon, Bo Ji,
• Abstract summary: Multi-Agent Debate (MAD) has emerged as a promising framework that engages multiple agents in structured debates.<n>We propose intelligent Multi-Agent Debate (iMAD), a token-efficient framework that selectively triggers MAD only when it is likely to be beneficial.<n>We show that iMAD significantly reduces token usage (by up to 92%) while also improving final answer accuracy (by up to 13.5%)
• Score: 11.86992814928132
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large Language Model (LLM) agent systems have advanced rapidly, driven by their strong generalization in zero-shot settings. To further enhance reasoning and accuracy on complex tasks, Multi-Agent Debate (MAD) has emerged as a promising framework that engages multiple LLM agents in structured debates to encourage diverse reasoning. However, triggering MAD for every query is inefficient, as it incurs substantial computational (token) cost and may even degrade accuracy by overturning correct single-agent answers. To address these limitations, we propose intelligent Multi-Agent Debate (iMAD), a token-efficient framework that selectively triggers MAD only when it is likely to be beneficial (i.e., correcting an initially wrong answer). To achieve this goal, iMAD learns generalizable model behaviors to make accurate debate decisions. Specifically, iMAD first prompts a single agent to produce a structured self-critique response, from which we extract 41 interpretable linguistic and semantic features capturing hesitation cues. Then, iMAD uses a lightweight debate-decision classifier, trained using our proposed FocusCal loss, to determine whether to trigger MAD, enabling robust debate decisions without test dataset-specific tuning. Through extensive experiments using six (visual) question answering datasets against five competitive baselines, we have shown that iMAD significantly reduces token usage (by up to 92%) while also improving final answer accuracy (by up to 13.5%).

Related papers

• Prepare Reasoning Language Models for Multi-Agent Debate with Self-Debate Reinforcement Learning [49.99694105650486]
  Self-Debate Reinforcement Learning (SDRL) is a training framework that equips a single large language model with strong problem-solving ability.<n>We show that SDRL improves overall Multi-Agent Debate (MAD) performance while simultaneously strengthening single model reasoning.
  arXiv  Detail & Related papers  (2026-01-29T20:21:44Z)
• Tool-MAD: A Multi-Agent Debate Framework for Fact Verification with Diverse Tool Augmentation and Adaptive Retrieval [10.62333858188658]
  Multi-Agent Debate (MAD) systems aim to improve answer accuracy by enabling multiple LLM agents to engage in dialogue.<n>Existing MAD frameworks primarily rely on internal knowledge or static documents, making them vulnerable to hallucinations.<n>We propose Tool-MAD, a multi-agent debate framework that enhances factual verification by assigning each agent a distinct external tool.
  arXiv  Detail & Related papers  (2026-01-08T09:07:41Z)
• M3MAD-Bench: Are Multi-Agent Debates Really Effective Across Domains and Modalities? [37.902089112579]
  Multi-Agent Debate (MAD) orchestrates multiple agents through structured debate to improve answer quality and support complex reasoning.<n>Existing research on MAD suffers from two fundamental limitations: evaluations are conducted under fragmented and inconsistent settings, hindering fair comparison.<n>We introduce M3MAD-Bench, a unified benchmark for evaluating MAD methods across Multi-domain tasks, Multi-modal inputs, and Multi-dimensional metrics.
  arXiv  Detail & Related papers  (2026-01-06T09:33:48Z)
• Multimodal Reinforcement Learning with Agentic Verifier for AI Agents [131.46008226323423]
  Argos is a principled multimodal reward agent to train reasoning models for agentic tasks.<n>By leveraging our agentic verifier across both SFT data and RL training, our model achieves state-of-the-art results.
  arXiv  Detail & Related papers  (2025-12-03T04:42:47Z)
• Towards Scalable Oversight with Collaborative Multi-Agent Debate in Error Detection [81.52796950244705]
  Self-diagnosis is unreliable on complex tasks unless aided by reliable external feedback.<n>We introduce a new collaborative MAD protocol, termed ColMAD, that reframes MAD as a non-zero sum game.<n>We show that ColMAD significantly outperforms previous competitive MAD by 19%.
  arXiv  Detail & Related papers  (2025-10-23T19:46:00Z)
• MADIAVE: Multi-Agent Debate for Implicit Attribute Value Extraction [52.89860691282002]
  Implicit Attribute Value Extraction (AVE) is essential for accurately representing products in e-commerce.<n>Despite advances in multimodal large language models (MLLMs), implicit AVE remains challenging due to the complexity of multidimensional data.<n>We introduce textscmodelname, a multi-agent debate framework that employs multiple MLLM agents to iteratively refine inferences.
  arXiv  Detail & Related papers  (2025-10-07T06:27:42Z)
• Free-MAD: Consensus-Free Multi-Agent Debate [17.384699873512464]
  Multi-agent debate (MAD) is an emerging approach to improving the reasoning capabilities of large language models (LLMs)<n>Existing MAD methods rely on multiple rounds of interaction among agents to reach consensus, and the final output is selected by majority voting in the last round.<n>We propose textscFree-MAD, a novel MAD framework that eliminates the need for consensus among agents.
  arXiv  Detail & Related papers  (2025-09-14T01:55:01Z)
• CortexDebate: Debating Sparsely and Equally for Multi-Agent Debate [11.155092859033784]
  Multi-Agent Debate (MAD) has emerged as an effective strategy to mitigate issues with single Large Language Model (LLM)<n>Existing MAD methods face two major issues: (a) too lengthy input contexts, which causes LLM agents to get lost in plenty of input information and experiences performance drop; and (b) the overconfidence dilemma, where self-assured LLM agents dominate the debate, leading to low debating effectiveness.<n>We propose a novel MAD method called "CortexDebate", inspired by the human brain's tendency to establish a sparse and dynamically optimized network among cortical areas governed by white matter.
  arXiv  Detail & Related papers  (2025-07-05T07:23:15Z)
• Revisiting Multi-Agent Debate as Test-Time Scaling: A Systematic Study of Conditional Effectiveness [50.29739337771454]
  Multi-agent debate (MAD) approaches offer improved reasoning, robustness, and diverse perspectives over monolithic models.<n>This paper conceptualizes MAD as a test-time computational scaling technique, distinguished by collaborative refinement and diverse exploration capabilities.<n>We conduct a comprehensive empirical investigation comparing MAD with strong self-agent test-time scaling baselines on mathematical reasoning and safety-related tasks.
  arXiv  Detail & Related papers  (2025-05-29T01:02:55Z)
• Stop Overvaluing Multi-Agent Debate -- We Must Rethink Evaluation and Embrace Model Heterogeneity [20.408720462383158]
  Multi-agent debate (MAD) has gained significant attention as a promising line of research to improve the factual accuracy and reasoning capabilities of large language models (LLMs)<n>Despite its conceptual appeal, current MAD research suffers from critical limitations in evaluation practices.<n>This paper presents a systematic evaluation of 5 representative MAD methods across 9 benchmarks using 4 foundational models.
  arXiv  Detail & Related papers  (2025-02-12T21:01:10Z)
• Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate [85.3444184685235]
  We propose a Multi-Agent Debate (MAD) framework, in which multiple agents express their arguments in the state of "tit for tat" and a judge manages the debate process to obtain a final solution. Our framework encourages divergent thinking in LLMs which would be helpful for tasks that require deep levels of contemplation.
  arXiv  Detail & Related papers  (2023-05-30T15:25:45Z)

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.