Metraipolis › archive › dc_c2b11b2ed556
MedicalHarness: A Controlled Evaluation of LLMs and Agent Harnesses on Medical Tasks — arXiv:2610.05778
- Source
- arXiv
- Original
- https://arxiv.org/abs/2610.05778
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-06T05:28:24.425Z
- SHA-256 of the archived text
4211d5a5c908375bce31cc28f778b26b519face8c19305c7d7aee39323dded14- Stable URL of this page
https://metraipolis.com/documento/dc_c2b11b2ed556
How to cite
MedicalHarness: A Controlled Evaluation of LLMs and Agent Harnesses on Medical Tasks — arXiv:2610.05778 — arXiv, https://arxiv.org/abs/2610.05778 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c2b11b2ed556 (Metraipolis archive dc_c2b11b2ed556, sha256 4211d5a5c908375bce31cc28f778b26b519face8c19305c7d7aee39323dded14)
BibTeX
@misc{dcc2b11b2ed556,
title = {MedicalHarness: A Controlled Evaluation of LLMs and Agent Harnesses on Medical Tasks — arXiv:2610.05778},
howpublished = {arXiv},
url = {https://arxiv.org/abs/2610.05778},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c2b11b2ed556; sha256 4211d5a5c908375bce31cc28f778b26b519face8c19305c7d7aee39323dded14},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.05778. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
LLM agents are increasingly built for medical work and scored on clinical benchmarks. Each such score, however, comes from a model running inside an agent harness, the system that controls the loop between the model and its environment. An agent's score is therefore a property of a model--harness pair. For medical agents, how much outcomes change with the harness has rarely been measured. Measuring this change, and explaining it, raises two challenges. First, a harness comparison must change nothing but the harness and be repeated across models and kinds of task. Second, comparing whole harnesses leaves their mechanisms bundled together, so it cannot show when an individual mechanism helps. To address these challenges, we present MedicalHarness, a controlled study of models and agent harnesses on medical tasks. We first build MedicalHarnessBench to evaluate agents on $107$ tasks across four domains that each test a different harness capability. Using this benchmark, we run five open-weight models under five agent harnesses, changing only the harness within a comparison, and analyze both outcomes and execution traces. To study individual mechanisms, we build MH-Lab, a controlled harness that switches off context management, planning or tool exposure one at a time within a shared execution loop. We find that the harness and its interaction with the model account for about a quarter of the outcome variance, and that no single harness is best across models and tasks. Code and data are available at this https URL . Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.CL, nuovi lavori del giorno). Categorie arXiv: Computation and Language (cs.CL). Pagina del lavoro: https://arxiv.org/abs/2610.05778 — 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 2026-10-06T05:24:20.344Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).