ArogyaSutra: A Multi-Agent Framework for Multimodal Medical Reasoning in Indic Languages
Summary
ArogyaBodha dataset and ArogyaSutra framework enhance multilingual medical reasoning in low-resource settings through diverse data integration and actor-critic multi-agent reasoning.
View Cached Full Text
Cached at: 06/12/26, 10:52 AM
Paper page - ArogyaSutra: A Multi-Agent Framework for Multimodal Medical Reasoning in Indic Languages
Source: https://huggingface.co/papers/2606.13572
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 andlow-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 integratestool groundingwithdual-memory mechanismsfor step-wise, reasoning-aware decision making, and uses stored actor-critic simulation trajectories fordistillation. Experiments show that our dataset and framework improvemultilingual medical reasoningaccuracy 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/
View arXiv pageView PDFAdd to collection
Get this paper in your agent:
hf papers read 2606\.13572
Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash
Models citing this paper0
No model linking this paper
Cite arxiv.org/abs/2606.13572 in a model README.md to link it from this page.
Datasets citing this paper0
No dataset linking this paper
Cite arxiv.org/abs/2606.13572 in a dataset README.md to link it from this page.
Spaces citing this paper0
No Space linking this paper
Cite arxiv.org/abs/2606.13572 in a Space README.md to link it from this page.
Collections including this paper0
No Collection including this paper
Add this paper to acollectionto link it from this page.
Similar Articles
SEMA-RAG: A Self-Evolving Multi-Agent Retrieval-Augmented Generation Framework for Medical Reasoning
SEMA-RAG is a self-evolving multi-agent RAG framework for medical question answering that decouples interpretation, exploration, and adjudication into three specialist agents, achieving significant accuracy improvements over baselines across multiple benchmarks.
IndicMedDialog: A Parallel Multi-Turn Medical Dialogue Dataset for Accessible Healthcare in Indic Languages
IndicMedDialog is a parallel multi-turn medical dialogue dataset spanning English and nine Indic languages, with a fine-tuned model for personalized symptom elicitation. The dataset is derived from MDDial, enhanced with LLM-generated synthetic consultations and expert verification, supporting multilingual healthcare AI.
Toward Vibe Medicine: A Self-Evolving Multi-Agent Framework for Clinical Decision Support
This paper presents VIBEMed, a multi-agent framework with a self-evolution mechanism and safety sandbox for robust clinical decision support, integrating specialized agents for diagnosis, treatment planning, and evolving clinical knowledge over time.
MODF-SIR: A Multi-agent Omni-modal Distilled Framework for Social Intelligence Reasoning
This paper proposes MODF-SIR, a multi-agent collaborative framework built on a lightweight multimodal large language model for social intelligence reasoning. It employs knowledge distillation, long-tail event extraction, and test-time adaptation to achieve state-of-the-art results with reduced training data.
BioInsight: Multi-Agent Orchestration for Interactive Biomedical Knowledge Discovery
BioInsight is a multi-agent system that transforms static biomedical reports into interactive, evidence-centered interfaces by organizing disease-specific evidence through structured artifacts and deterministic citation normalization.