Metraipolis › archive › dc_4785defd7fb4
Frozen Models, Evolving Expertise: Model-Agnostic Learning from Deployment Experience for Multimodal Medical AI — arXiv:2610.09146
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.09146
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T11:09:01.563Z
- SHA-256 of the archived text
a1aeb9fce517750ae85b0c22cc98cc0dd6580c9d627184b510570e7d0ebd6493- Stable URL of this page
https://metraipolis.com/documento/dc_4785defd7fb4
How to cite
Frozen Models, Evolving Expertise: Model-Agnostic Learning from Deployment Experience for Multimodal Medical AI — arXiv:2610.09146 — arXiv (en), https://arxiv.org/abs/2610.09146 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_4785defd7fb4 (Metraipolis archive dc_4785defd7fb4, sha256 a1aeb9fce517750ae85b0c22cc98cc0dd6580c9d627184b510570e7d0ebd6493)
BibTeX
@misc{dc4785defd7fb4,
title = {Frozen Models, Evolving Expertise: Model-Agnostic Learning from Deployment Experience for Multimodal Medical AI — arXiv:2610.09146},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.09146},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_4785defd7fb4; sha256 a1aeb9fce517750ae85b0c22cc98cc0dd6580c9d627184b510570e7d0ebd6493},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.09146. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Large language models (LLMs) and vision-language models (VLMs) are usually frozen after deployment, so they do not learn from the cases they solve. This is especially concerning in medicine, where new clinical evidence, updated guidelines, and new therapies can change established practice. Fine-tuning can update the model, but it requires access to model weights and additional training. Parameter-free methods avoid training, but they may overfit a fixed validation set, lack reliable domain knowledge, or lose visual details by saving experience only as text. To address these limitations, we present a model-agnostic framework that allows frozen LLMs and VLMs to learn from deployment experience through three forms of external expertise: a Skill that guides reasoning and tool use, a Knowledge Memory that stores reliable facts supported by earlier cases or trusted external evidence, and a Multimodal Knowledge Base that keeps visual examples and guides the model to relate each retrieved case to the current image. Instead of relying on a fixed validation set, a validation strategy keeps an update only if it helps on new cases without degrading performance on earlier ones. Across six benchmarks covering clinical diagnosis, clinical workflows, medical reasoning, and medical and non-medical visual reasoning, and with four open-weight and closed-source base models, our framework improves performance during online deployment by up to 34.2% over the base model on medical tasks, generalizes to unseen cases, transfers to other models without further optimization, and works in non-medical domains. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2610.09146 — 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 2026-10-08T10:14:05.910Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).