Metraipolis › archive › dc_59ae78b784aa
ActiveMedAgent: Cost-Aware Trajectory Learning for Multimodal Medical Diagnosis — arXiv:2610.11140
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.11140
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-09T05:57:09.933Z
- SHA-256 of the archived text
107ce4e41b22d8aca35aa91048840d40f5341d35043e837a3cca9ca448431fcc- Stable URL of this page
https://metraipolis.com/documento/dc_59ae78b784aa
How to cite
ActiveMedAgent: Cost-Aware Trajectory Learning for Multimodal Medical Diagnosis — arXiv:2610.11140 — arXiv (en), https://arxiv.org/abs/2610.11140 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_59ae78b784aa (Metraipolis archive dc_59ae78b784aa, sha256 107ce4e41b22d8aca35aa91048840d40f5341d35043e837a3cca9ca448431fcc)
BibTeX
@misc{dc59ae78b784aa,
title = {ActiveMedAgent: Cost-Aware Trajectory Learning for Multimodal Medical Diagnosis — arXiv:2610.11140},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.11140},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_59ae78b784aa; sha256 107ce4e41b22d8aca35aa91048840d40f5341d35043e837a3cca9ca448431fcc},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.11140. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Clinical diagnosis is inherently sequential: clinicians escalate from cheap to costly tests only when additional evidence is expected to resolve diagnostic uncertainty. We present ActiveMedAgent, a framework that brings this cost-aware sequential logic to multimodal medical AI. Given a frozen, API-accessed vision-language model, ActiveMedAgent tracks probability distributions over candidate diagnoses and scores each acquisition by its per-step diagnostic utility minus cost. A lightweight MLP controller is then trained offline on these scored trajectories, learning when to request additional evidence and when to commit. Across three commonly used benchmarks, trajectory-based policy learning consistently outperforms both unguided acquisition and full-modality baselines. Notably, we identify an information overload effect. In 175 cases, the agent produces a correct diagnosis with fewer channels while the full-modality baseline fails, showing that learning what to omit can be as important as learning what to acquire. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Computer Vision and Pattern Recognition (cs.CV); Multimedia (cs.MM). Pagina del lavoro: https://arxiv.org/abs/2610.11140 — 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 2026-10-09T05:47:01.508Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).