Metraipolis › archive › dc_cee0ab0ceef4
Fathom-Vaidya: Advancing Medical Reasoning with Rubric-Based Rewards — arXiv:2609.24480
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.24480
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-09T06:50:40.935Z
- SHA-256 of the archived text
3f712bb1f797d9b4f972d9736f7648077a087c1246d184d6eb0d4e1166c26374- Stable URL of this page
https://metraipolis.com/documento/dc_cee0ab0ceef4
How to cite
Fathom-Vaidya: Advancing Medical Reasoning with Rubric-Based Rewards — arXiv:2609.24480 — arXiv (en), https://arxiv.org/abs/2609.24480 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_cee0ab0ceef4 (Metraipolis archive dc_cee0ab0ceef4, sha256 3f712bb1f797d9b4f972d9736f7648077a087c1246d184d6eb0d4e1166c26374)
BibTeX
@misc{dccee0ab0ceef4,
title = {Fathom-Vaidya: Advancing Medical Reasoning with Rubric-Based Rewards — arXiv:2609.24480},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.24480},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_cee0ab0ceef4; sha256 3f712bb1f797d9b4f972d9736f7648077a087c1246d184d6eb0d4e1166c26374},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.24480. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-22 in cs.CL). Categorie arXiv: Artificial Intelligence (cs.AI) ; Computation and Language (cs.CL); Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2609.24480 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-09T06:48:45.145Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-22?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).