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

• URL: http://arxiv.org/abs/2608.13476v1
• Date: Thu, 13 Aug 2026 17:00:08 GMT
• Title: MARC v1: An Open-Source Multi-Agent Framework for Clinical AI Reasoning and Coordination
• Abstract summary: MARC coordinates role-specialized agents for extraction, reasoning, answer generation, and evaluation.<n>Decomposer module generates task-specific agent prompts from a plain-language description.<n>MARC is designed to be model-agnostic, interpretable, and accessible to clinical domain experts without programming expertise.
• Score: 2.3475925378848124
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Inference-Time Graph Engineering for Multi-Agent LLM Workflows [51.56038180639833]
  We introduce ReActNet, a training-free framework that compiles a query and a set of role-specialized agents into a sequence of directed communication graphs.<n>We show that ReActNet consistently improves over fixed-topology and learned-topology baselines while maintaining competitive inference cost.
  arXiv  Detail & Related papers  (2026-09-04T23:32:11Z)
• Benchmarking AI Agents for Hardware Design Automation via MCP Tool Calling [1.6639892342953113]
  We ask whether AI agents powered by locally deployed large language models can reliably automate expert-defined hardware design in an industry-realistic tool-calling setting.<n>To study this setting, we build a Model Context Protocol (MCP) server that reproduces the state and dependency logic of a proprietary hardware design tool used in embedded system development.<n>We evaluate seven open-source models comparing pipeline choices including system prompts, tool-description detail, context scope, and single-agent versus multi-agent architectures.
  arXiv  Detail & Related papers  (2026-08-25T15:33:50Z)
• Provable Coordination for LLM Agents via Message Sequence Charts [0.0]
  We introduce a domain-specific language for specifying agent coordination based on message sequence charts (MSCs)<n>We define the syntax and semantics of the language and present a syntax-directed projection that generates deadlock-free local agent programs from global coordination specifications.<n>An open-source Python implementation of our framework is available as ZipperGen.
  arXiv  Detail & Related papers  (2026-04-19T20:54:30Z)
• Interpretable Context Methodology: Folder Structure as Agentic Architecture [0.0]
  Current approaches to AI agent orchestration typically involve building multi-agent frameworks that manage context passing, memory, error handling, and step coordination through code.<n>This paper presents Model Workspace Protocol (MWP), a method that replaces framework-level orchestration with structure.<n>Plain markdown files carry the prompts and context that tell a single AI agent what role to play at each step. Local scripts handle the mechanical work that does not need AI at all.
  arXiv  Detail & Related papers  (2026-03-17T00:03:23Z)
• DeALOG: Decentralized Multi-Agents Log-Mediated Reasoning Framework [7.772295511115406]
  DeALOG is a decentralized multi-agent framework for multimodal question answering.<n>It uses specialized agents: Table, Context, Visual, Summarizing and Verification.
  arXiv  Detail & Related papers  (2026-02-01T03:26:52Z)
• Rethinking Testing for LLM Applications: Characteristics, Challenges, and a Lightweight Interaction Protocol [83.83217247686402]
  Large Language Models (LLMs) have evolved from simple text generators into complex software systems that integrate retrieval augmentation, tool invocation, and multi-turn interactions.<n>Their inherent non-determinism, dynamism, and context dependence pose fundamental challenges for quality assurance.<n>This paper decomposes LLM applications into a three-layer architecture: textbftextitSystem Shell Layer, textbftextitPrompt Orchestration Layer, and textbftextitLLM Inference Core.
  arXiv  Detail & Related papers  (2025-08-28T13:00:28Z)
• PC-Agent: A Hierarchical Multi-Agent Collaboration Framework for Complex Task Automation on PC [98.82146219495792]
  In this paper, we propose a hierarchical agent framework named PC-Agent.<n>From the perception perspective, we devise an Active Perception Module (APM) to overcome the inadequate abilities of current MLLMs in perceiving screenshot content.<n>From the decision-making perspective, to handle complex user instructions and interdependent subtasks more effectively, we propose a hierarchical multi-agent collaboration architecture.
  arXiv  Detail & Related papers  (2025-02-20T05:41:55Z)
• Talk Structurally, Act Hierarchically: A Collaborative Framework for LLM Multi-Agent Systems [10.67359331022116]
  textitTalk Structurally, Act Hierarchically (TalkHier) is a novel framework that introduces a structured communication protocol for context-rich exchanges.<n>textitTalkHier surpasses various types of SoTA, including inference scaling model (OpenAI-o1), open-source multi-agent models (e.g., AgentVerse)
  arXiv  Detail & Related papers  (2025-02-16T12:26:58Z)
• CRAB: Cross-environment Agent Benchmark for Multimodal Language Model Agents [49.68117560675367]
  Crab is the first benchmark framework designed to support cross-environment tasks.<n>Our framework supports multiple devices and can be easily extended to any environment with a Python interface.<n>The experimental results demonstrate that the single agent with GPT-4o achieves the best completion ratio of 38.01%.
  arXiv  Detail & Related papers  (2024-07-01T17:55:04Z)
• AgentKit: Structured LLM Reasoning with Dynamic Graphs [91.09525140733987]
  We propose an intuitive LLM prompting framework (AgentKit) for multifunctional agents. AgentKit offers a unified framework for explicitly constructing a complex "thought process" from simple natural language prompts.
  arXiv  Detail & Related papers  (2024-04-17T15:40:45Z)
• TaskWeaver: A Code-First Agent Framework [50.99683051759488]
  TaskWeaver is a code-first framework for building LLM-powered autonomous agents. It converts user requests into executable code and treats user-defined plugins as callable functions. It provides support for rich data structures, flexible plugin usage, and dynamic plugin selection.
  arXiv  Detail & Related papers  (2023-11-29T11:23:42Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.