Metraipolis › archive › dc_703219b6e2ca
MIRA: Medical Image Reflection for Agentic Diagnosis — arXiv:2608.10827
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.10827
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-19T06:09:30.363Z
- SHA-256 of the archived text
1acc66851c1d63a866e25f9a37dfe7bda17a4e77b8e44f10aa7f93447662c5fe- Stable URL of this page
https://metraipolis.com/documento/dc_703219b6e2ca
How to cite
MIRA: Medical Image Reflection for Agentic Diagnosis — arXiv:2608.10827 — arXiv (en), https://arxiv.org/abs/2608.10827 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_703219b6e2ca (Metraipolis archive dc_703219b6e2ca, sha256 1acc66851c1d63a866e25f9a37dfe7bda17a4e77b8e44f10aa7f93447662c5fe)
BibTeX
@misc{dc703219b6e2ca,
title = {MIRA: Medical Image Reflection for Agentic Diagnosis — arXiv:2608.10827},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.10827},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_703219b6e2ca; sha256 1acc66851c1d63a866e25f9a37dfe7bda17a4e77b8e44f10aa7f93447662c5fe},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.10827. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Medical visual agents can use tools to inspect images and retrieve external knowledge, but indiscriminate tool use may introduce noisy or misleading evidence. Reliable diagnosis therefore requires not only acquiring additional observations, but also verifying whether tool actions are necessary and whether the resulting evidence supports the current hypothesis. We introduce MIRA (Medical Image Reflection for Agentic Diagnosis), a medical visual diagnostic framework for autonomous evidence search and reflective verification. MIRA dynamically invokes image-processing operations, including zooming, grounding, pointing, rotation, and measurement, as well as web search, while evaluating the relevance and consistency of the acquired evidence. We develop MIRA through a two-stage training strategy. First, a tool-augmented Monte Carlo Tree Search data engine explores diverse diagnostic hypotheses and jointly verifies visual grounding accuracy and semantic consistency to construct supervised fine-tuning trajectories. Second, reinforcement learning further improves decision-making through online reflective principle evolution: failure cases are distilled into candidate principles, and only principles that improve held-out rollout rewards are retained. Across nine medical visual reasoning benchmarks, MIRA achieves an average score of 64.73, improving its Qwen3-VL-8B backbone by 7.44 points. It also increases useful tool-use judgments from 56.2% to 73.8% and reduces harmful judgments from 8.9% to 1.6%. Qualitative analyses show that MIRA can re-examine evidence, correct premature conclusions, and adapt its tool-use strategy. Project page: this https URL Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-12 in cs.AI). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2608.10827 — 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 2026-10-19T05:57:28.410Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-12?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).