MedMASLab: Medical Vision-Language Multi-Agent Benchmarking Data

MedMASLab is a benchmarking dataset for medical vision-language multi-agent systems released by qyhhhhh in March 2026. It provides standardized data and metrics for evaluating how multiple AI agents collaborate on medical visual question answering tasks. The dataset is associated with Arxiv paper 2603.09909 and focuses on multi-agent coordination in clinical AI.

Use Cases

• Evaluating multi-agent coordination using medical visual question answering (VQA) pairs
• Benchmarking vision-language models on clinical diagnostic reasoning tasks
• Testing communication protocols between agents using the provided medical image-text pairs

Strengths

• MIT licensed for open academic and commercial research
• Linked to Arxiv 2603.09909 for peer-reviewed methodology
• Specifically targets multi-agent system (MAS) architectures rather than single models

Limitations

• Metadata does not specify the total number of images or text records
• Column names and specific data schema are not provided in the repository overview

Provenance

Source

Arxiv paper 2603.09909

Freshness

Last updated March 2026.

Geography

Region: US