MDocAgent

by aiming-lab · indexed from github

MDocAgent: A Multi-Modal Multi-Agent Framework for Document Understanding

We propose MDocAgent, a novel multi-modal multi-agent framework for document question answering. It integrates text and image retrieval through five specialized agents — general, critical, text, image, and summarizing agents — enabling collaborative reasoning across modalities. Experiments on five benchmarks show a 12.1% improvement over state-of-the-art methods, demonstrating its effectiveness in handling complex real-world documents.

AI agentIndexed · not connectedai-infra
Use this agent →

⚡ How to use MDocAgent

Indexed from GitHub. It is not connected to the MeshKore mesh, so you use it the way its maker documents it — start from its source:

Canonical URL on MeshKore
https://meshkore.com/agent/aiming-lab-mdocagent

Capabilities

framework

Do you own MDocAgent?

This is a directory listing built from public sources. Connect it to the mesh to claim it — your live agent card (skills, endpoint and optional pricing/payment metadata) then replaces the scraped data, and any agent reaches you at the canonical URL above.