# MARC v1: An Open-Source Multi-Agent Framework for Clinical AI Reasoning and Coordination

arXiv: https://arxiv.org/abs/2608.13476 · HTML: https://mlsanity.com/paper/2608.13476/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Clinical and biomedical applications, one of 17 directions in LLM reasoning.
- Builds on 8 of its 22 references that are in the map.
- First posted on arXiv 13 Aug 2026.

## Placed in

- LLM reasoning / [Clinical and biomedical applications](https://mlsanity.com/lr/clinical-and-biomedical-applications/)
- LLM agents and tool use / [Medical and scientific domain agents](https://mlsanity.com/agents/medical-and-scientific-domain-agents/)

## Builds on (most cited first, 8 of 8)

- [Capabilities of GPT-4 on Medical Challenge Problems](https://mlsanity.com/paper/2303.13375/) (2023)
- [MedGemma Technical Report](https://mlsanity.com/paper/2507.05201/) (2025)
- [Capabilities of GPT-5 on Multimodal Medical Reasoning](https://mlsanity.com/paper/2508.08224/) (2025)
- [Generative to Agentic AI: Survey, Conceptualization, and Challenges](https://mlsanity.com/paper/2504.18875/) (2025)
- [RadFabric: Agentic AI System with Reasoning Capability for Radiology](https://mlsanity.com/paper/2506.14142/) (2025)
- [Multi-step retrieval and reasoning improves radiology question answering with large language models](https://mlsanity.com/paper/2508.00743/) (2025)
- [Best Practices for Large Language Models in Radiology](https://mlsanity.com/paper/2412.01233/) (2024)
- [Retrieval-Augmented Generation in Medicine: A Scoping Review of Technical Implementations, Clinical Applications, and Ethical Considerations](https://mlsanity.com/paper/2511.05901/) (2025)

## Abstract (arXiv)

We present Multi-Agent Reasoning and Coordination (MARC), an open-source framework that replaces monolithic LLM prompting with deterministic multi-agent orchestration for clinical reasoning. MARC coordinates role-specialized agents for extraction, reasoning, answer generation, and evaluation, with explicit context passing and traceable intermediate outputs, enabling stage-wise failure attribution. We additionally introduce a Decomposer module that generates task-specific agent prompts from a plain-language description, eliminating manual prompt engineering. The framework supports both API-based and local CPU-compatible deployments and is entirely configurable via YAML, without code modifications. MARC is designed to be model-agnostic, interpretable, and accessible to clinical domain experts without programming expertise. The full framework is available at https://github.com/Penn-RAIL/MARC-v1.