MARC v1: An Open-Source Multi-Agent Framework for Clinical AI Reasoning and Coordination
Provides developers with a structured framework for building interpretable clinical AI systems with traceable reasoning and model-agnostic deployment.
AI Summary
Researchers release MARC v1, an open-source multi-agent framework for clinical AI reasoning that replaces monolithic LLM prompting with deterministic agent orchestration.
Excerpt
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 pla