MARC v1：一个用于临床AI推理与协作的开源多智能体框架
MARC v1: An Open-Source Multi-Agent Framework for Clinical AI Reasoning and Coordination
浏览论文内容
中文总结 AI 辅助
该研究提出开源多智能体框架MARC v1，以确定性多智能体编排替代整体式LLM提示用于临床推理，含角色专业化智能体与分解器模块，支持多部署方式，具备模型无关、可解释等特性。
中文摘要 AI 辅助
我们提出了多智能体推理与协作框架MARC，它是一个开源框架，用于临床推理中，以确定性多智能体编排替代整体式大语言模型（LLM）提示。MARC协调角色专业化智能体，负责提取、推理、答案生成与评估，具备显式上下文传递与可追溯中间输出，支持阶段性故障归因。我们还引入了分解器模块，可从纯语言描述生成任务特定智能体提示，消除手动提示工程。该框架支持基于API的部署及本地CPU兼容部署，完全通过YAML配置，无需代码修改，设计为模型无关、可解释，可供无编程专业知识的临床领域专家使用。完整框架可通过此https URL获取。
英文摘要
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.
