Metraipolis › archive › dc_9cd8ede30e0a
MedRouter: Demystifying Knowledge Differences Across Medical LLMs for Routing-Based Reasoning — arXiv:2609.33119
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.33119
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T21:01:02.218Z
- SHA-256 of the archived text
5a62c17d7600e9fd648eb15ca6ee0ce9d08f59f5336a75dce91cd3a710aee14f- Stable URL of this page
https://metraipolis.com/documento/dc_9cd8ede30e0a
How to cite
MedRouter: Demystifying Knowledge Differences Across Medical LLMs for Routing-Based Reasoning — arXiv:2609.33119 — arXiv (en), https://arxiv.org/abs/2609.33119 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_9cd8ede30e0a (Metraipolis archive dc_9cd8ede30e0a, sha256 5a62c17d7600e9fd648eb15ca6ee0ce9d08f59f5336a75dce91cd3a710aee14f)
BibTeX
@misc{dc9cd8ede30e0a,
title = {MedRouter: Demystifying Knowledge Differences Across Medical LLMs for Routing-Based Reasoning — arXiv:2609.33119},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.33119},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_9cd8ede30e0a; sha256 5a62c17d7600e9fd648eb15ca6ee0ce9d08f59f5336a75dce91cd3a710aee14f},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.33119. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Medical question answering spans diverse specialties and modalities, and individual medical large language models (LLMs) exhibit distinct strengths across tasks and domains. This heterogeneity suggests that combining specialists may enable broader coverage of medical questions than relying on any single model. However, existing LLM routing methods primarily seek to balance answer quality and inference cost, leaving open how to exploit differences in specialist competence to improve medical reasoning. In this paper, we introduce MedRouter, an agentic system that uses an embedding-based multi-label router to select and query specialist LLMs, then passes their responses to a generator to produce the final answer. We further propose SCALE (Specialist Competence-Aware Learning), a two-stage training framework that first trains the Router with specialist correctness supervision and then optimizes its selections through reinforcement learning. The second stage uses a Performance Gain Reward (PGR) that measures how specialist information affects the generator's answer correctness relative to answering without that information. Experiments on eight text-based and multimodal medical QA benchmarks show that MedRouter outperforms the strongest routing baseline by 8% in average accuracy. Our analysis of specialist outputs further reveals distinct strengths and complementary question-level coverage, motivating learned routing to combine these capabilities for more comprehensive medical reasoning. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.AI). Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2609.33119 — 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 2026-10-07T20:29:02.549Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).