From Conflict to Consensus: Boosting Medical Reasoning via Multi-Round Agentic RAG

• URL: http://arxiv.org/abs/2603.03292v1
• Date: Fri, 06 Feb 2026 08:25:30 GMT
• Title: From Conflict to Consensus: Boosting Medical Reasoning via Multi-Round Agentic RAG
• Abstract summary: Large Language Models (LLMs) exhibit high reasoning capacity in medical question-answering.<n>Their tendency to produce hallucinations and outdated knowledge poses critical risks in healthcare fields.<n>Existing methods rely on noisy token-level signals and lack the multi-round refinement required for complex reasoning.
• Score: 65.0203623486525
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large Language Models (LLMs) exhibit high reasoning capacity in medical question-answering, but their tendency to produce hallucinations and outdated knowledge poses critical risks in healthcare fields. While Retrieval-Augmented Generation (RAG) mitigates these issues, existing methods rely on noisy token-level signals and lack the multi-round refinement required for complex reasoning. In the paper, we propose **MA-RAG** (**M**ulti-Round **A**gentic RAG), a framework that facilitates test-time scaling for complex medical reasoning by iteratively evolving both external evidence and internal reasoning history within an agentic refinement loop. At each round, the agent transforms semantic **conflict** among candidate responses into actionable queries to retrieve external evidence, while optimizing history reasoning traces to mitigate long-context degradation. MA-RAG extends the *self-consistency* principle by leveraging the lack of consistency as a proactive signal for multi-round agentic reasoning and retrieval, and mirrors a *boosting* mechanism that iteratively minimizes the residual error toward a stable, high-fidelity medical **consensus**. Extensive evaluations across 7 medical Q&A benchmarks show that MA-RAG consistently surpasses competitive inference-time scaling and RAG baselines, delivering **substantial +6.8 points** on average accuracy over the backbone model. Our code is available at [this url](https://github.com/NJU-RL/MA-RAG).

Related papers

• 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)
• Synergistic Perception-Reasoning Governance: Grounding Medical MLLMs with Verifiable Anatomical Evidence [45.78409219344429]
  Multimodal large language models (MLLMs) show strong promise for clinical VQA and radiology report generation, yet inference-time hallucinations undermine trustworthy use.<n>We propose a holistic, training-free evidence-injection framework that systematically mitigates hallucinations through dual-side evidence injection.<n>We conduct systematic evaluations on 2 tasks and 5 datasets using textttLLaVA-1.5-7B, texttLLaVA-Med-1.5-7B, texttQwen3-VL-8B/32B, and textttInternVL
  arXiv  Detail & Related papers  (2026-06-30T08:07:25Z)
• SEMA-RAG: A Self-Evolving Multi-Agent Retrieval-Augmented Generation Framework for Medical Reasoning [23.915129702519817]
  We propose a Self-Evolving Multi-Agent RAG framework for medical question answering.<n>It assigns these roles to three specialist agents: the Interpreter Agent for clinical schema interpretation, the Explorer Agent for sufficiency-driven retrieval, and the Arbiter Agent for evidence adjudication and answer selection.<n>It improves the strongest baseline by +6.46 accuracy points on average, measured per backbone.
  arXiv  Detail & Related papers  (2026-05-16T18:09:47Z)
• Eliciting Medical Reasoning with Knowledge-enhanced Data Synthesis: A Semi-Supervised Reinforcement Learning Approach [62.0906177191353]
  Existing approaches distill chain-of-thought reasoning traces from large proprietary models via supervised fine-tuning, then conduct reinforcement learning (RL)<n>We propose MedSSR, a Medical Knowledge-enhanced data Synthesis and Semi-supervised Reinforcement learning framework.<n>Our framework first employs rare disease knowledge to synthesize distribution-controllable reasoning questions.<n>We then utilize the policy model itself to generate high-quality pseudo-labels. This enables a two-stage, intrinsic-to-extrinsic training paradigm: self-supervised RL on the pseudo-labeled data, followed by supervised RL on the human-annotated real data
  arXiv  Detail & Related papers  (2026-04-13T14:37:38Z)
• Doctor-RAG: Failure-Aware Repair for Agentic Retrieval-Augmented Generation [23.961760006898157]
  Agentic Retrieval-Augmented Generation (Agentic RAG) has become a widely adopted paradigm for question answering and complex knowledge reasoning.<n>Existing approaches typically address such failures by either stopping at diagnostic analysis or rerunning the entire retrieval-reasoning pipeline.<n>We propose Doctor-RAG, a unified diagnose-and-repair framework that corrects failures in Agentic RAG through explicit error localization and prefix reuse.
  arXiv  Detail & Related papers  (2026-04-01T13:13:27Z)
• MuISQA: Multi-Intent Retrieval-Augmented Generation for Scientific Question Answering [16.26521741515184]
  Multi-Intent Scientific Question Answering (MuISQA) benchmark designed to evaluate RAG systems on heterogeneous evidence coverage across sub-questions.<n>In addition, we propose an intent-aware retrieval framework that leverages large language models (LLMs) to hypothesize potential answers, decompose them into intent-specific queries, and retrieve supporting passages for each underlying intent.<n>Experiments on both MuISQA benchmark and other general RAG datasets demonstrate that our method consistently outperforms conventional approaches, particularly in retrieval accuracy and evidence coverage.
  arXiv  Detail & Related papers  (2025-11-20T12:03:36Z)
• MIRAGE: Scaling Test-Time Inference with Parallel Graph-Retrieval-Augmented Reasoning Chains [19.018680886214035]
  MIRAGE (Multi-chain Inference with Retrieval-Augmented Graph Exploration) is a novel test-time scalable reasoning framework.<n>It performs dynamic multi-chain inference over structured medical knowledge graphs.<n>It consistently outperforms GPT-4o, Tree-of-Thought variants, and other retrieval-augmented baselines in both automatic and human evaluations.
  arXiv  Detail & Related papers  (2025-08-25T17:53:22Z)
• MedCoT-RAG: Causal Chain-of-Thought RAG for Medical Question Answering [4.285647375182588]
  Large language models (LLMs) have shown promise in medical question answering but often struggle with hallucinations and shallow reasoning.<n>Retrieval-augmented generation (RAG) offers a practical and privacy-preserving way to enhance LLMs with external medical knowledge.<n>We introduce MedCoT-RAG, a domain-specific framework that combines causal-aware document retrieval with structured chain-of-thought prompting.
  arXiv  Detail & Related papers  (2025-08-20T05:43:26Z)
• Towards Agentic RAG with Deep Reasoning: A Survey of RAG-Reasoning Systems in LLMs [69.10441885629787]
  Retrieval-Augmented Generation (RAG) lifts the factuality of Large Language Models (LLMs) by injecting external knowledge.<n>It falls short on problems that demand multi-step inference; conversely, purely reasoning-oriented approaches often hallucinate or mis-ground facts.<n>This survey synthesizes both strands under a unified reasoning-retrieval perspective.
  arXiv  Detail & Related papers  (2025-07-13T03:29:41Z)
• Talk Before You Retrieve: Agent-Led Discussions for Better RAG in Medical QA [17.823588070044217]
  We propose Discuss-RAG, a plug-and-play module designed to enhance the medical question answering system.<n>Our method introduces a summarizer agent that orchestrates a team of medical experts to emulate multi-turn brainstorming, thereby improving the relevance of retrieved content.<n> Experimental results on four benchmark medical QA datasets show that Discuss-RAG consistently outperforms MedRAG.
  arXiv  Detail & Related papers  (2025-04-30T01:37:44Z)
• Retrieval is Not Enough: Enhancing RAG Reasoning through Test-Time Critique and Optimization [58.390885294401066]
  Retrieval-augmented generation (RAG) has become a widely adopted paradigm for enabling knowledge-grounded large language models (LLMs)<n>RAG pipelines often fail to ensure that model reasoning remains consistent with the evidence retrieved, leading to factual inconsistencies or unsupported conclusions.<n>We propose AlignRAG, a novel iterative framework grounded in Critique-Driven Alignment (CDA)<n>We introduce AlignRAG-auto, an autonomous variant that dynamically terminates refinement, removing the need to pre-specify the number of critique iterations.
  arXiv  Detail & Related papers  (2025-04-21T04:56:47Z)
• 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)
• CDF-RAG: Causal Dynamic Feedback for Adaptive Retrieval-Augmented Generation [3.8808821719659763]
  We introduce Causal Dynamic Feedback for Adaptive Retrieval-Augmented Generation (CDF-RAG)<n>CDF-RAG iteratively refines queries, retrieves structured causal graphs, and enables multi-hop causal reasoning across interconnected knowledge sources.<n>We evaluate CDF-RAG on four diverse datasets, demonstrating its ability to improve response accuracy and causal correctness over existing RAG-based methods.
  arXiv  Detail & Related papers  (2025-04-17T01:15:13Z)

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.