An agentic framework for enhancing multimodal medical reasoning in Indian Languages.</p>\n","updatedAt":"2026-06-12T09:54:51.794Z","author":{"_id":"630e850c3fc17ffc50f752e5","avatarUrl":"/avatars/43e4aee228323211b8cf55b783cc54d2.svg","fullname":"Akash Ghosh","name":"Agcs12","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.8078284859657288},"editors":["Agcs12"],"editorAvatarUrls":["/avatars/43e4aee228323211b8cf55b783cc54d2.svg"],"reactions":[],"isReport":false}}],"primaryEmailConfirmed":false,"paper":{"id":"2606.13572","authors":[{"_id":"6a2b80b74957fcdd3aac06fa","name":"Tanmoy Kanti Halder","hidden":false},{"_id":"6a2b80b74957fcdd3aac06fb","name":"Akash Ghosh","hidden":false},{"_id":"6a2b80b74957fcdd3aac06fc","name":"Subhadip Baidya","hidden":false},{"_id":"6a2b80b74957fcdd3aac06fd","name":"Arijit Roy","hidden":false},{"_id":"6a2b80b74957fcdd3aac06fe","name":"Sriparna Saha","hidden":false}],"publishedAt":"2026-06-11T00:00:00.000Z","submittedOnDailyAt":"2026-06-12T00:00:00.000Z","title":"ArogyaSutra: A Multi-Agent Framework for Multimodal Medical Reasoning in Indic Languages","submittedOnDailyBy":{"_id":"630e850c3fc17ffc50f752e5","avatarUrl":"/avatars/43e4aee228323211b8cf55b783cc54d2.svg","isPro":false,"fullname":"Akash Ghosh","user":"Agcs12","type":"user","name":"Agcs12"},"summary":"Multimodal Large Language Models (MLLMs) have shown promising reasoning capabilities in general domains, yet their performance remains limited in specialized settings such as healthcare, especially in multilingual and low-resource scenarios. This gap is critical in regions like rural India, where patients often express complex medical queries in native Indic languages and rely on multimodal inputs such as medical images. Existing English-centric MLLMs struggle to support such use cases, limiting equitable access to AI-driven healthcare assistance. To address this challenge, we introduce ArogyaBodha, a large-scale multilingual multimodal medical question-answer dataset constructed from eight heterogeneous sources, covering 31 body systems, six imaging modalities, and 21 clinical domains across English and seven major Indian languages. We further propose ArogyaSutra, an actor-critic-based multi-agent framework that integrates tool grounding with dual-memory mechanisms for step-wise, reasoning-aware decision making, and uses stored actor-critic simulation trajectories for distillation. Experiments show that our dataset and framework improve multilingual medical reasoning accuracy across all Indic languages, with ablations validating the contribution of each component. The source code and dataset are available at: https://iitp-cse.github.io/ ArogyaSutra/","upvotes":2,"discussionId":"6a2b80b74957fcdd3aac06ff","ai_summary":"ArogyaBodha dataset and ArogyaSutra framework enhance multilingual medical reasoning in low-resource settings through diverse data integration and actor-critic multi-agent reasoning.","ai_keywords":["Multimodal Large Language Models","tool grounding","dual-memory mechanisms","actor-critic framework","step-wise reasoning","distillation","multilingual medical reasoning","low-resource scenarios"],"ai_summary_model":"Qwen/Qwen2.5-Coder-32B-Instruct","organization":{"_id":"66960bd10e08a6505b87086e","name":"IITPatna01","fullname":"IIT Patna","avatar":"https://cdn-avatars.huggingface.co/v1/production/uploads/66960b121de9b5a5f25628da/KKmrySyMfUy5N0nv54REB.png"}},"canReadDatabase":false,"canManagePapers":false,"canSubmit":false,"hasHfLevelAccess":false,"upvoted":false,"upvoters":[{"_id":"630e850c3fc17ffc50f752e5","avatarUrl":"/avatars/43e4aee228323211b8cf55b783cc54d2.svg","isPro":false,"fullname":"Akash Ghosh","user":"Agcs12","type":"user"},{"_id":"6270324ebecab9e2dcf245de","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/6270324ebecab9e2dcf245de/cMbtWSasyNlYc9hvsEEzt.jpeg","isPro":false,"fullname":"Kye Gomez","user":"kye","type":"user"}],"acceptLanguages":["en"],"dailyPaperRank":0,"organization":{"_id":"66960bd10e08a6505b87086e","name":"IITPatna01","fullname":"IIT Patna","avatar":"https://cdn-avatars.huggingface.co/v1/production/uploads/66960b121de9b5a5f25628da/KKmrySyMfUy5N0nv54REB.png"},"markdownContentUrl":"https://huggingface.co/buckets/huggingchat/papers-content/resolve/2606/2606.13572.md","query":{}}">
ArogyaSutra: A Multi-Agent Framework for Multimodal Medical Reasoning in Indic Languages
Abstract
ArogyaBodha dataset and ArogyaSutra framework enhance multilingual medical reasoning in low-resource settings through diverse data integration and actor-critic multi-agent reasoning.
Multimodal Large Language Models (MLLMs) have shown promising reasoning capabilities in general domains, yet their performance remains limited in specialized settings such as healthcare, especially in multilingual and low-resource scenarios. This gap is critical in regions like rural India, where patients often express complex medical queries in native Indic languages and rely on multimodal inputs such as medical images. Existing English-centric MLLMs struggle to support such use cases, limiting equitable access to AI-driven healthcare assistance. To address this challenge, we introduce ArogyaBodha, a large-scale multilingual multimodal medical question-answer dataset constructed from eight heterogeneous sources, covering 31 body systems, six imaging modalities, and 21 clinical domains across English and seven major Indian languages. We further propose ArogyaSutra, an actor-critic-based multi-agent framework that integrates tool grounding with dual-memory mechanisms for step-wise, reasoning-aware decision making, and uses stored actor-critic simulation trajectories for distillation. Experiments show that our dataset and framework improve multilingual medical reasoning accuracy across all Indic languages, with ablations validating the contribution of each component. The source code and dataset are available at: https://iitp-cse.github.io/ ArogyaSutra/
Community
An agentic framework for enhancing multimodal medical reasoning in Indian Languages.
Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.
Tap or paste here to upload images
Cite arxiv.org/abs/2606.13572 in a model README.md to link it from this page.
Cite arxiv.org/abs/2606.13572 in a dataset README.md to link it from this page.
Cite arxiv.org/abs/2606.13572 in a Space README.md to link it from this page.
Discussion (0)
Sign in to join the discussion. Free account, 30 seconds — email code or GitHub.
Sign in →No comments yet. Sign in and be the first to say something.