MAPLE: Elevating Medical Reasoning from Statistical Consensus to Process-Led Alignment

• URL: http://arxiv.org/abs/2603.08987v1
• Date: Mon, 09 Mar 2026 22:22:57 GMT
• Title: MAPLE: Elevating Medical Reasoning from Statistical Consensus to Process-Led Alignment
• Abstract summary: We propose a novel and unified training paradigm that integrates medical process reward models with Test-Time Reinforcement Learning (TTRL)<n>Specifically, we advance the TTRL framework by replacing the conventional MV with a fine-grained, expert-aligned supervision paradigm using Med-RPM.<n>This integration ensures that reinforcement learning is guided by medical correctness rather than mere consensus, effectively distilling search-based intelligence into the model's parametric memory.
• Score: 40.18486858532692
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent advances in medical large language models have explored Test-Time Reinforcement Learning (TTRL) to enhance reasoning. However, standard TTRL often relies on majority voting (MV) as a heuristic supervision signal, which can be unreliable in complex medical scenarios where the most frequent reasoning path is not necessarily the clinically correct one. In this work, we propose a novel and unified training paradigm that integrates medical process reward models with TTRL to bridge the gap between test-time scaling (TTS) and parametric model optimization. Specifically, we advance the TTRL framework by replacing the conventional MV with a fine-grained, expert-aligned supervision paradigm using Med-RPM. This integration ensures that reinforcement learning is guided by medical correctness rather than mere consensus, effectively distilling search-based intelligence into the model's parametric memory. Extensive evaluations on four different benchmarks have demonstrated that our developed method consistently and significantly outperforms current TTRL and standalone PRM selection. Our findings establish that transitioning from stochastic heuristics to structured, step-wise rewards is essential for developing reliable and scalable medical AI systems

Related papers

• 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)
• Meta-TTRL: A Metacognitive Framework for Self-Improving Test-Time Reinforcement Learning in Unified Multimodal Models [13.234585564123485]
  Existing test-time scaling methods for unified multimodal models (UMMs) in text-to-image (T2I) generation rely on search or sampling strategies.<n>We propose Meta-TTRL, a metacognitive test-time reinforcement learning framework.<n>Extensive experiments demonstrate that Meta-TTRL generalizes well across three representative UMMs.
  arXiv  Detail & Related papers  (2026-03-16T17:28:57Z)
• MedAD-R1: Eliciting Consistent Reasoning in Interpretible Medical Anomaly Detection via Consistency-Reinforced Policy Optimization [46.65200216642429]
  We introduce MedAD-38K, the first large-scale, multi-modal, and multi-center benchmark for MedAD featuring diagnostic Chain-of-Thought (CoT) annotations alongside structured Visual Question-Answering (VQA) pairs.<n>Our proposed model, MedAD-R1, achieves state-of-the-art (SOTA) performance on the MedAD-38K benchmark, outperforming strong baselines by more than 10%.
  arXiv  Detail & Related papers  (2026-02-01T07:56:10Z)
• MMedExpert-R1: Strengthening Multimodal Medical Reasoning via Domain-Specific Adaptation and Clinical Guideline Reinforcement [63.82954136824963]
  Medical Vision-Language Models excel at perception tasks with complex clinical reasoning required in real-world scenarios.<n>We propose a novel reasoning MedVLM that addresses these challenges through domain-specific adaptation and guideline reinforcement.
  arXiv  Detail & Related papers  (2026-01-16T02:32:07Z)
• TCM-Eval: An Expert-Level Dynamic and Extensible Benchmark for Traditional Chinese Medicine [51.01817637808011]
  We introduce TCM-Eval, the first dynamic and high-quality benchmark for Traditional Chinese Medicine (TCM)<n>We construct a large-scale training corpus and propose Self-Iterative Chain-of-Thought Enhancement (SI-CoTE)<n>Using this enriched training data, we develop ZhiMingTang (ZMT), a state-of-the-art LLM specifically designed for TCM.
  arXiv  Detail & Related papers  (2025-11-10T14:35:25Z)
• MedAlign: A Synergistic Framework of Multimodal Preference Optimization and Federated Meta-Cognitive Reasoning [52.064286116035134]
  We develop MedAlign, a framework to ensure visually accurate LVLM responses for Medical Visual Question Answering (Med-VQA)<n>We first propose a multimodal Direct Preference Optimization (mDPO) objective to align preference learning with visual context.<n>We then design a Retrieval-Aware Mixture-of-Experts (RA-MoE) architecture that utilizes image and text similarity to route queries to a specialized and context-augmented LVLM.
  arXiv  Detail & Related papers  (2025-10-24T02:11:05Z)
• An Agentic Model Context Protocol Framework for Medical Concept Standardization [5.12407270785129]
  We develop a zero-training, hallucination-preventive mapping system based on the Model Context Protocol (MCP)<n>The system enables explainable mapping and significantly improves efficiency and accuracy with minimal effort.
  arXiv  Detail & Related papers  (2025-09-04T02:32:22Z)
• RPRO: Ranked Preference Reinforcement Optimization for Enhancing Medical QA and Diagnostic Reasoning [5.493679122639688]
  Medical question answering requires advanced reasoning that integrates domain knowledge with logical inference.<n>We propose Ranked Preference Reinforcement Optimization (RPRO), a novel framework that combines reinforcement learning with preference-driven reasoning refinement.
  arXiv  Detail & Related papers  (2025-08-31T19:38:25Z)
• Transforming Multimodal Models into Action Models for Radiotherapy [39.682133213072554]
  Radiotherapy a crucial cancer treatment demands precise planning to balance tumor preservation and eradication of healthy tissue.<n>Traditional treatment planning (TP) is iterative, time-consuming, and reliant on human expertise.<n>We propose a novel framework to transform a multimodal foundation model (MLM) into an action model for using a few-shot reinforcement learning approach.
  arXiv  Detail & Related papers  (2025-02-06T09:51:28Z)

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.