{"ID":2864921,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.02328","arxiv_id":"2510.02328","title":"AMANDA: Agentic Medical Knowledge Augmentation for Data-Efficient Medical Visual Question Answering","abstract":"Medical Multimodal Large Language Models (Med-MLLMs) have shown great promise in medical visual question answering (Med-VQA). However, when deployed in low-resource settings where abundant labeled data are unavailable, existing Med-MLLMs commonly fail due to their medical reasoning capability bottlenecks: (i) the intrinsic reasoning bottleneck that ignores the details from the medical image; (ii) the extrinsic reasoning bottleneck that fails to incorporate specialized medical knowledge. To address those limitations, we propose AMANDA, a training-free agentic framework that performs medical knowledge augmentation via LLM agents. Specifically, our intrinsic medical knowledge augmentation focuses on coarse-to-fine question decomposition for comprehensive diagnosis, while extrinsic medical knowledge augmentation grounds the reasoning process via biomedical knowledge graph retrieval. Extensive experiments across eight Med-VQA benchmarks demonstrate substantial improvements in both zero-shot and few-shot Med-VQA settings. The code is available at https://github.com/REAL-Lab-NU/AMANDA.","short_abstract":"Medical Multimodal Large Language Models (Med-MLLMs) have shown great promise in medical visual question answering (Med-VQA). However, when deployed in low-resource settings where abundant labeled data are unavailable, existing Med-MLLMs commonly fail due to their medical reasoning capability bottlenecks: (i) the intri...","url_abs":"https://arxiv.org/abs/2510.02328","url_pdf":"https://arxiv.org/pdf/2510.02328v1","authors":"[\"Ziqing Wang\",\"Chengsheng Mao\",\"Xiaole Wen\",\"Yuan Luo\",\"Kaize Ding\"]","published":"2025-09-26T01:22:25Z","proceeding":"cs.CL","tasks":"[\"cs.CL\",\"cs.AI\",\"cs.MA\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false,"code_links":[{"ID":609213,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2864921,"paper_url":"https://arxiv.org/abs/2510.02328","paper_title":"AMANDA: Agentic Medical Knowledge Augmentation for Data-Efficient Medical Visual Question Answering","repo_url":"https://github.com/REAL-Lab-NU/AMANDA","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}