Process-Supervised Multi-Agent Reinforcement Learning for Reliable Clinical Reasoning

• URL: http://arxiv.org/abs/2602.14160v1
• Date: Sun, 15 Feb 2026 14:21:21 GMT
• Title: Process-Supervised Multi-Agent Reinforcement Learning for Reliable Clinical Reasoning
• Authors: Chaeeun Lee, T. Michael Yates, Pasquale Minervini, T. Ian Simpson,
• Abstract summary: We introduce an agent-as-tool reinforcement learning framework for gene-disease validity curation.<n>One critical real-world case is gene-disease validity curation, where experts must determine whether a gene is causally implicated in a disease.<n>Our evaluation shows that with outcome-only rewards, MAS with a GRPO-trained supervisor agent substantially improves final outcome accuracy from 0.195 with a base model supervisor to 0.732.<n>With process + outcome rewards, MAS with GRPO-trained supervisor achieves higher outcome accuracy (0.750) while significantly improving process fidelity to 0.520 F1.
• Score: 15.47321745394914
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Clinical decision-making requires nuanced reasoning over heterogeneous evidence and traceable justifications. While recent LLM multi-agent systems (MAS) show promise, they largely optimise for outcome accuracy while overlooking process-grounded reasoning aligned with clinical standards. One critical real-world case of this is gene-disease validity curation, where experts must determine whether a gene is causally implicated in a disease by synthesising diverse biomedical evidence. We introduce an agent-as-tool reinforcement learning framework for this task with two objectives: (i) process-level supervision to ensure reasoning follows valid clinical pathways, and (ii) efficient coordination via a hierarchical multi-agent system. Our evaluation on the ClinGen dataset shows that with outcome-only rewards, MAS with a GRPO-trained Qwen3-4B supervisor agent substantially improves final outcome accuracy from 0.195 with a base model supervisor to 0.732, but results in poor process alignment (0.392 F1). Conversely, with process + outcome rewards, MAS with GRPO-trained supervisor achieves higher outcome accuracy (0.750) while significantly improving process fidelity to 0.520 F1. Our code is available at https://github.com/chaeeunlee-io/GeneDiseaseCurationAgents.

Related papers

• Guideline-Grounded Evidence Accumulation for High-Stakes Agent Verification [60.18369393468405]
  Existing verifiers usually underperform owing to a lack of domain knowledge and limited calibration.<n>GLEAN compiles expert-curated protocols into trajectory-informed, well-calibrated correctness signals.<n>We empirically validate GLEAN with agentic clinical diagnosis across three diseases from the MIMIC-IV dataset.
  arXiv  Detail & Related papers  (2026-03-03T09:36:43Z)
• CARE: Towards Clinical Accountability in Multi-Modal Medical Reasoning with an Evidence-Grounded Agentic Framework [29.22693846221723]
  We introduce CARE, advancing Clinical Accountability in multi-modal medical Reasoning with an Evidence-grounded agentic framework.<n> CARE decomposes the task into coordinated sub-modules to reduce shortcut learning and hallucination.<n>Our CARE-Flow improves average accuracy by 10.9% over the same size (10B) state-of-the-art (SOTA)
  arXiv  Detail & Related papers  (2026-03-02T08:38:37Z)
• A Multi-Agent Framework for Medical AI: Leveraging Fine-Tuned GPT, LLaMA, and DeepSeek R1 for Evidence-Based and Bias-Aware Clinical Query Processing [0.4349324020366305]
  Large language models (LLMs) show promise for healthcare question answering, but clinical use is limited by weak verification, insufficient evidence grounding, and unreliable confidence signalling.<n>We propose a multi-agent medical QA framework that combines complementary LLMs with evidence retrieval, uncertainty estimation, and bias checks to improve answer reliability.
  arXiv  Detail & Related papers  (2026-02-15T14:17:27Z)
• CVeDRL: An Efficient Code Verifier via Difficulty-aware Reinforcement Learning [57.24524263804788]
  Code verifiers play a critical role in post-verification for LLM-based code generation.<n>Existing supervised fine-tuning methods suffer from data scarcity, high failure rates, and poor inference efficiency.<n>We show that naive RL with only functionality rewards fails to generate effective unit tests for difficult branches and samples.
  arXiv  Detail & Related papers  (2026-01-30T10:33:29Z)
• Developing Fairness-Aware Task Decomposition to Improve Equity in Post-Spinal Fusion Complication Prediction [3.860970992977915]
  We propose a fairness-aware multitask learning framework for postoperative complication prediction.<n> FAIR-MTL employs a data-driven subgroup inference mechanism.<n>It achieves an AUC of 0.86 and an accuracy of 75%, outperforming single-task baselines while substantially reducing bias.
  arXiv  Detail & Related papers  (2025-11-29T19:06:07Z)
• Repurposing Synthetic Data for Fine-grained Search Agent Supervision [81.95597592711688]
  LLM-based search agents are increasingly trained on entity-centric synthetic data.<n> prevailing training methods discard this rich entity information, relying instead on sparse, outcome-based rewards.<n>We introduce Entity-aware Group Relative Policy Optimization (E-GRPO), a novel framework that formulates a dense entity-aware reward function.
  arXiv  Detail & Related papers  (2025-10-28T17:50:40Z)
• DispatchMAS: Fusing taxonomy and artificial intelligence agents for emergency medical services [49.70819009392778]
  Large Language Models (LLMs) and Multi-Agent Systems (MAS) offer opportunities to augment dispatchers.<n>This study aimed to develop and evaluate a taxonomy-grounded, multi-agent system for simulating realistic scenarios.
  arXiv  Detail & Related papers  (2025-10-24T08:01:21Z)
• A Fully Automatic Framework for Intracranial Pressure Grading: Integrating Keyframe Identification, ONSD Measurement and Clinical Data [3.6652537579778106]
  Intracranial pressure (ICP) elevation poses severe threats to cerebral function, thus necessitating monitoring for timely intervention.<n>We introduce a fully automatic two-stage framework for ICP grading, integrating ONSD measurement and clinical data.<n>Our method achieves a validation accuracy of $0.845 pm 0.071$ and an independent test accuracy of 0.786, significantly outperforming conventional threshold-based method.
  arXiv  Detail & Related papers  (2025-09-11T11:37:48Z)
• Organ-Agents: Virtual Human Physiology Simulator via LLMs [66.40796430669158]
  Organ-Agents is a multi-agent framework that simulates human physiology via LLM-driven agents.<n>We curated data from 7,134 sepsis patients and 7,895 controls, generating high-resolution trajectories across 9 systems and 125 variables.<n>Organ-Agents achieved high simulation accuracy on 4,509 held-out patients, with per-system MSEs 0.16 and robustness across SOFA-based severity strata.
  arXiv  Detail & Related papers  (2025-08-20T01:58:45Z)
• Quantifying the Reasoning Abilities of LLMs on Real-world Clinical Cases [48.87360916431396]
  We introduce MedR-Bench, a benchmarking dataset of 1,453 structured patient cases, annotated with reasoning references.<n>We propose a framework encompassing three critical examination recommendation, diagnostic decision-making, and treatment planning, simulating the entire patient care journey.<n>Using this benchmark, we evaluate five state-of-the-art reasoning LLMs, including DeepSeek-R1, OpenAI-o3-mini, and Gemini-2.0-Flash Thinking, etc.
  arXiv  Detail & Related papers  (2025-03-06T18:35:39Z)

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.