Fathom-Vaidya: Advancing Medical Reasoning with Rubric-Based Rewards

原文：Fathom-Vaidya: Advancing Medical Reasoning with Rubric-Based Rewards

作者：Kalash Shah, Kunal Singh, Snehan J, Shreyas Singh

来源：arXiv cs.LG（机器学习）

正文

Computer Science > Artificial Intelligence

arXiv:2609.24480v1 (cs)

[Submitted on 21 Sep 2026]

Title:Fathom-Vaidya: Advancing Medical Reasoning with Rubric-Based Rewards

Authors:Kalash Shah, Kunal Singh, Snehan J, Shreyas Singh

View a PDF of the paper titled Fathom-Vaidya: Advancing Medical Reasoning with Rubric-Based Rewards, by Kalash Shah and 3 other authors

View PDF

HTML (experimental)

Abstract:Deploying Large Language Models (LLMs) in healthcare requires robust performance across two complementary dimensions - diagnostic reasoning: the convergent, evidence-driven task of inferring a patient’s condition from clinical data to produce a diagnosis, and clinical healthcare reasoning: the broader, navigational judgment required to communicate, plan, and adapt across multi-turn clinical interactions where a single correct answer may not exist. Recent benchmarks such as HealthBench and MedXpertQA reveal persistent weaknesses in both areas, exposing failures in complex diagnostic scenarios and limitations in contextual, patient-centered dialogue. We introduce a sequential training framework that targets these facets using synthetic data and rubric-based reinforcement learning. First, we improve diagnostic reasoning using MedBullets-derived questions with rule- and rubric-guided Reinforcement Learning (RL). We then shift to clinical reasoning by generating 5.3k synthetic multi-turn scenarios, each paired with multi-dimensional rubrics to comprehensively assess the response. This approach yields over 10% improvement on MedXpertQA, and our 30B model achieves 50.1% accuracy on HealthBench-Hard, surpassing proprietary baselines including GPT-5 (thinking). Our results show that targeted synthetic datasets and rubric-based training can systematically improve both diagnostic and interactive clinical reasoning in medical LLMs.

Comments:

18 pages, 5 Figures, Correspondence to this http URL@fractal.ai

Subjects:

Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Machine Learning (cs.LG)

Cite as:

arXiv:2609.24480 [cs.AI]

(or

arXiv:2609.24480v1 [cs.AI] for this version)

https://doi.org/10.48550/arXiv.2609.24480

Focus to learn more

arXiv-issued DOI via DataCite (pending registration)

主题

人工智能 · 自然语言处理 · 机器学习

由「前沿雷达」于 2026-09-21 采集。正文取自原文页面，已保留出处链接。标题与正文版权归原作者所有。