ARMOR-MAD: Adaptive Routing for Heterogeneous Multi-Agent Debate in Large Language Model Reasoning

• URL: http://arxiv.org/abs/2606.13197v1
• Date: Thu, 11 Jun 2026 11:02:19 GMT
• Title: ARMOR-MAD: Adaptive Routing for Heterogeneous Multi-Agent Debate in Large Language Model Reasoning
• Abstract summary: ARMOR-MAD is a training-free heterogeneous MAD framework that treats debate as conditional computation.<n>We show that ARMOR-MAD consistently improves over fixed-round heterogeneous debate with the same model pool.
• Score: 4.363650510090806
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Multi-agent debate (MAD) can improve large language model reasoning, but fixed debate pipelines often waste computation and can amplify correlated errors among similar agents. We propose ARMOR-MAD, a training-free heterogeneous MAD framework that treats debate as conditional computation. ARMOR-MAD combines three components: Pre-debate Agreement Routing (PAR) decides whether independently generated Round-0 answers require debate; Early Agreement Stopping Evaluator (EASE) stops debate after convergence; and Semantic Outlier Detection (SOD) down-weights abnormal final answers during aggregation. Across MATH Level 5, GSM8K, MMLU, and MMLU-Pro, ARMOR-MAD consistently improves over fixed-round heterogeneous debate with the same model pool, reaching 65.5\%, 96.5\%, 90.0\%, and 81.5\% accuracy, respectively. The results suggest that genuine model heterogeneity and agreement-based control are both important for making MAD more accurate and efficient.

Related papers

• Remember and Reweight: Enhancing Multi-Agent Debate with Experience Memory and Confidence Estimation [6.5331167606521205]
  Multi-agent debate (MAD) improves the reasoning capabilities of large language models by having multiple agents iteratively refine their responses through discussion.<n>MAD suffers from a critical vulnerability known as shared misconception: when a majority of agents converge on an incorrect answer, the debate process tends to amplify rather than correct the error.<n>Existing methods primarily address peer skew but leave the agents' inherently biased concept priors unaddressed.<n>We propose R$2$-MAD, a framework that equips agents with an experience memory accumulated from past debates.
  arXiv  Detail & Related papers  (2026-09-03T10:05:01Z)
• MIRAGE: Defending Long-Form RAG Against Misinformation Pollution [87.40537931342082]
  We introduce MIRAGE, a training-free, model-agnostic defense for long-form RAG.<n>MIRAGE builds an NLI-based cross-document claim graph and applies a Defended-Claims Gate to either condition generation on a consistent, multi-source supported subset or to block retrieval and answer parametrically.
  arXiv  Detail & Related papers  (2026-07-06T13:36:12Z)
• MAIGO: Mitigating Lost-in-Conversation with History-Cleaned On-Policy Self-Distillation [51.32912774464992]
  Large language models often solve tasks from a fully specified prompt but degrade when the same requirements unfold over multiple turns.<n>We propose MAIGO, an on-policy self-distillation method that reduces this contamination using history-cleaned references from the model's own policy.<n>For middle turns, MAIGO removes prior assistant replies while preserving the user-visible sharded prefix; for answer turns, it distills from paired full-view references conditioned on the completed user-side dialogue.
  arXiv  Detail & Related papers  (2026-05-26T15:38:46Z)
• Heterogeneous Consensus-Progressive Reasoning for Efficient Multi-Agent Debate [58.675713546748305]
  Multi-Agent Debate (MAD) is a collaborative framework in which multiple agents iteratively refine solutions through the generation of reasoning and alternating critique cycles.<n>This work introduces Heterogeneous Consensus-Progressive Reasoning for Efficient Multi-Agent Debate (HCP-MAD)<n>HCP-MAD employs a three-stage progressive reasoning mechanism to develop adaptive solutions across varying task complexities.
  arXiv  Detail & Related papers  (2026-04-03T06:58:59Z)
• 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)
• iMAD: Intelligent Multi-Agent Debate for Efficient and Accurate LLM Inference [11.86992814928132]
  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%)
  arXiv  Detail & Related papers  (2025-11-14T13:50:51Z)
• 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)
• 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)
• Debate or Vote: Which Yields Better Decisions in Multi-Agent Large Language Models? [13.569822165805851]
  Multi-Agent Debate(MAD) has emerged as a promising paradigm for improving the performance of large language models.<n>Despite recent advances, the key factors driving MAD's effectiveness remain unclear.<n>We disentangle MAD into two key components--Majority Voting and inter-agent Debate--and assess their respective contributions.
  arXiv  Detail & Related papers  (2025-08-24T22:14:32Z)
• Retrieval-Augmented Generation with Conflicting Evidence [57.66282463340297]
  Large language model (LLM) agents are increasingly employing retrieval-augmented generation (RAG) to improve the factuality of their responses.<n>In practice, these systems often need to handle ambiguous user queries and potentially conflicting information from multiple sources.<n>We propose RAMDocs (Retrieval with Ambiguity and Misinformation in Documents), a new dataset that simulates complex and realistic scenarios for conflicting evidence for a user query.
  arXiv  Detail & Related papers  (2025-04-17T16:46:11Z)

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.