AMANDA: Agentic Medical Knowledge Augmentation for Data-Efficient Medical Visual Question Answering

Medical Multimodal Large Language Models (Med-MLLMs) have shown great promise in medical visual question answering (Med-VQA).However, when deployed in lowresource 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 trainingfree 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.