arXiv AI October 31, 2026 By Gaurav Bhatt, Marinka Zitnik

Latent Decision Flow Rewards for Clinical Guideline Reasoning

The paper introduces GUIDER, a method that jointly trains a decision flow controller and a reasoning policy to improve clinical guideline reasoning. GUIDER generates multiple plausible decision flows from guideline supervision, computes process rewards across these flows, and gates them on answer correctness to address both path–answer gaps and path multiplicity. Experiments on MedGUIDE and out‑of‑domain benchmarks show that GUIDER outperforms existing reinforcement learning baselines, achieving higher weighted accuracy and guideline adherence.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv AI

Oct 15

Reinforcement Learning In Partially Verifiable Environments for Colon Cancer Treatment Planning

arXiv:2610.17426v1 Announce Type: cross Abstract: Clinical decision-making is a sequential process of information collection, clinical inference, and forecasting under partial observability, often wi...

By Li-Ching Chen, Andr\'es Franco Valiente, Yuta Ishiyama, Zachary R. Chalmers, William Chen, Kelsey Natsuhara, Taema Brinjikji, Madhumita Sushil, Travis Zack, Julian C. Hong

llms agents reinforcement-learning safety

arXiv Computer Vision

Oct 1

From Given to Gathered Evidence: Agentic Learning for Longitudinal Medical Reasoning

arXiv:2609.39566v1 Announce Type: new Abstract: Foundation models can serve as clinical agents through tool-use harnesses. However, conventional medical benchmarks assess reasoning over preselected e...

By Minye Shao, Chaohui Yu, Yixuan Wu, Fan Wang, Ling Shao, Yang Long

llms agents reinforcement-learning fine-tuning efficiency multimodal benchmarks

arXiv AI

Jun 30

An AI agent for treatment reasoning over a biomedical tool universe

arXiv:2606. 28692v1 Announce Type: new Abstract: Treatment reasoning underpins every therapeutic decision, integrating disease context, comorbidities, medications, contraindications, and evolving biomedical knowledge to select an appropriate therapy.

By Shanghua Gao, Ayush Noori, Richard Zhu, Curtis Ginder, Zhenglun Kong, Xiaorui Su, Justin Kauffman, Benjamin S. Glicksberg, Joshua Lampert, Ankit Sakhuja, Ashwin Sawant, ATHENA-R1 Evaluation Consortium, David A. Clifton, Noa Dagan, Ran Balicer, Marinka Zitnik

llms agents reinforcement-learning fine-tuning benchmarks

arXiv AI

Aug 25

BioMed-Agent-RL: A Meta Learning, All You Need for Biomedical Applications

arXiv:2608.21864v1 Announce Type: cross Abstract: The current progress of Clinical Vision Large Language Models (C-VLLMs) has substantially improved digital diagnostics, still these frameworks often...

By Md Asaduzzaman Jabin, Zihao Wu, Tianming Liu

llms agents reinforcement-learning multimodal benchmarks safety

arXiv AI

Oct 27

GRASP: Group-Adaptive Hybrid RL-SFT Post-Training for Medical VQA without Reasoning Annotations

arXiv:2610.34561v1 Announce Type: cross Abstract: Adapting general-purpose vision-language models (VLMs) to medical visual question answering (VQA) is valuable for helping clinicians read images and...

By Wanqi Dong, Wanyue Dong, Jingze Ge, Mehul Motani

llms nlp reinforcement-learning fine-tuning multimodal benchmarks

arXiv AI

6d ago

Aligning Medical Vision Language Models at the Capability Boundary with Entropy Adaptive Rubric Grounding

The paper introduces MedCBR, a two‑stage alignment framework for medical vision‑language models that improves diagnostic reasoning at the capability boundary. First, it uses Difficulty Weighted Boundary Preference Optimization (DBPO) to focus learning on counterfactual boundary cases, and second, it applies Entropy Gated Grounded Policy Optimization (EGPO) to reward anatomical grounding and reasoning fidelity while mitigating rubric noise. Experiments on six medical benchmarks demonstrate consistent accuracy gains, especially on challenging differential diagnosis tasks, with the combined stages delivering super‑additive improvements.

By Hongyu Bai, Jiaqi Zeng, Chunzheng Zhu

llms reinforcement-learning fine-tuning benchmarks safety

One email a morning, machine-written

Related stories

Reinforcement Learning In Partially Verifiable Environments for Colon Cancer Treatment Planning

From Given to Gathered Evidence: Agentic Learning for Longitudinal Medical Reasoning

An AI agent for treatment reasoning over a biomedical tool universe

BioMed-Agent-RL: A Meta Learning, All You Need for Biomedical Applications

GRASP: Group-Adaptive Hybrid RL-SFT Post-Training for Medical VQA without Reasoning Annotations

Aligning Medical Vision Language Models at the Capability Boundary with Entropy Adaptive Rubric Grounding