# AMANDA: Agentic Medical Knowledge Augmentation for Data-Efficient Medical Visual Question Answering Source: [AMANDA: Agentic Medical Knowledge Augmentation for Data-Efficient Medical Visual Question Answering]() Collection index: [llms.txt]() Data updated: 2025-10-26T05:49:23.746Z Authors: Ziqing Wang, Chengsheng Mao, Xiaole Wen, Yuan Luo, Kaize Ding Published: 2025-09-26T01:22:25.000Z ## 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. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. ## Original sources and implementation [Original paper]() [PDF]()