AMANDA: Agentic Medical Knowledge Augmentation for Data-Efficient Medical Visual Question Answering
On the map: Multimodal LLMs / vision-language models → Medical vision-language models
also in 1 more
Abstract (arXiv)
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.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in Medical vision-language models, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 17 of its 39 references that are in the map. First posted on arXiv 26 Sep 2025.
Builds on
17 of 39 references.
Closest ancestors · 4
Same direction, newest first
- 2024MC-CoT: A Modular Collaborative CoT Framework for Zero-shot Medical-VQA with LLM and MLLM Integration6 Oct
- 2024MMedAgent: Learning to Use Medical Tools with Multi-modal Agent2 Jul
- 2024Worse than Random? An Embarrassingly Simple Probing Evaluation of Large Multimodal Models in Medical VQA30 May
- 2024Vision-Language Models for Medical Report Generation and Visual Question Answering: A Review4 Mar
Other references · 13
- 2023ViperGPT: Visual Inference via Python Execution for Reasoningcited by 603
- 2021SLAKE: A Semantically-Labeled Knowledge-Enhanced Dataset for Medical Visual Question Answeringcited by 449
- 2020Generating Radiology Reports via Memory-driven Transformercited by 368
- 2024Benchmarking Retrieval-Augmented Generation for Medicinecited by 331
- 2023MedAgents: Large Language Models as Collaborators for Zero-shot Medical Reasoningcited by 316
- 2023BLIVA: A Simple Multimodal LLM for Better Handling of Text-Rich Visual Questionscited by 125
- 2021Medical Visual Question Answering: A Surveycited by 93
- 2022Plug-and-Play VQA: Zero-shot VQA by Conjoining Large Pretrained Models with Zero Trainingcited by 88
- 2024FairCLIP: Harnessing Fairness in Vision-Language Learningcited by 69
- 2022Align, Reason and Learn: Enhancing Medical Vision-and-Language Pre-training with Knowledgecited by 51
- 2024MEDCO: Medical Education Copilots Based on A Multi-Agent Frameworkcited by 33
- 2023Q2ATransformer: Improving Medical VQA via an Answer Querying Decodercited by 31
1 more
Built on by
Citing papers per year: 2026: 1.
1 paper.
Similar, not cited
Close in wording, no citation either way
- 2024LLM-MedQA: Enhancing Medical Question Answering through Case Studies in Large Language Models
- 2026MedProb: Probing Internal Representations of Vision-Language Models for Medical Question Answering
- 2026LiteMedCoT-VL: Parameter-Efficient Adaptation for Medical Visual Question Answering
- 2025MedXplain-VQA: Multi-Component Explainable Medical Visual Question Answering
- 2026MedLVR: Latent Visual Reasoning for Reliable Medical Visual Question Answering
- 2025Agentic Medical Knowledge Graphs Enhance Medical Question Answering: Bridging the Gap Between LLMs and Evolving Medical Knowledge
- 2025Multimodal Retrieval-Augmented Generation with Large Language Models for Medical VQA
- 2025ClinKD: Cross-Modal Clinical Knowledge Distiller For Multi-Task Medical Images