# MedBenchAgent: Towards Systematic Automation of Medical VLM Benchmark Construction

arXiv: https://arxiv.org/abs/2610.11312 · HTML: https://mlsanity.com/paper/2610.11312/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Medical vision-language models, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 14 of its 37 references that are in the map.
- First posted on arXiv 8 Oct 2026.

## Placed in

- Multimodal LLMs / vision-language models / [Medical vision-language models](https://mlsanity.com/mllm/medical-vision-language-models/)

## Builds on (most cited first, 14 of 14)

- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [Qwen3-VL Technical Report](https://mlsanity.com/paper/2511.21631/) (2025)
- [InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models](https://mlsanity.com/paper/2504.10479/) (2025)
- [Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models](https://mlsanity.com/paper/2506.05176/) (2025)
- [DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence](https://mlsanity.com/paper/2606.19348/) (2026)
- [Skin Lesion Analysis Toward Melanoma Detection 2018: A Challenge Hosted by the International Skin Imaging Collaboration (ISIC)](https://mlsanity.com/paper/1902.03368/) (2019)
- [MedGemma Technical Report](https://mlsanity.com/paper/2507.05201/) (2025)
- [PMC-VQA: Visual Instruction Tuning for Medical Visual Question Answering](https://mlsanity.com/paper/2305.10415/) (2023)
- [Lingshu: A Generalist Foundation Model for Unified Multimodal Medical Understanding and Reasoning](https://mlsanity.com/paper/2506.07044/) (2025)
- [Hulu-Med: A Transparent Generalist Model towards Holistic Medical Vision-Language Understanding](https://mlsanity.com/paper/2510.08668/) (2025)
- [Benchmark Everything Everywhere All at Once](https://mlsanity.com/paper/2606.06462/) (2026)
- [MMBU: A Massive Multi-modal Biomedical Understanding Benchmark to Probe the Perception Capabilities of Vision-Language Models](https://mlsanity.com/paper/2606.06696/) (2026)
- [Automated Report-Derived Oncology VQA Benchmark for Evaluating Vision-Language Models on 3D Medical Imaging](https://mlsanity.com/paper/2606.02809/) (2026)
- [BreastGPT: A Multimodal Large Language Model for the Full Spectrum of Breast Cancer Clinical Routine](https://mlsanity.com/paper/2606.04911/) (2026)

## Abstract (arXiv)

Large-scale construction of medical vision-language model (VLM) benchmarks is increasingly feasible with richly annotated imaging datasets and large language models (LLMs), yet existing automation largely focuses on generating evaluation items within predefined benchmark specifications. We study the broader problem of automatically deriving the specification itself: what to evaluate, which annotations support each task, and how to translate this evidence into reliable evaluation items. We formulate benchmark construction as constrained compilation, in which the benchmark specification is progressively derived from evaluation requirements, heterogeneous annotations, and medical knowledge. Based on this formulation, we introduce MedBenchAgent, a multi-agent framework with a Benchmark Intermediate Representation (BIR) that encodes task definitions, evidence mappings, evaluation protocols, and item specifications across construction stages. MedBenchAgent separates planning, which derives and verifies the specification, from instantiation, which constructs and audits items under the locked specification. MedBenchAgent achieves a Task-Space F1 of 90.9%, outperforming direct task induction (79.2-80.0%) and prior-guided induction (85.1%); 994 of 1,000 sampled items from correctly identified tasks pass human audit. We further demonstrate portability to a specialized medical domain and evaluate twelve VLMs, revealing task- and setting-specific variation obscured by aggregate scores. These results establish constrained compilation as a scalable and auditable framework for medical VLM benchmark construction beyond question generation.