MASFactory: A Graph-centric Framework for Orchestrating LLM-Based Multi-Agent Systems with Vibe Graphing

2026-03-06

AI Summary

This work proposes MASFactory, a graph-centric framework for multi-agent systems that addresses the limitations of existing approaches, which rely heavily on manual coding to construct complex graph-based workflows, resulting in poor reusability and difficulty integrating heterogeneous external contexts. MASFactory introduces Vibe Graphing, a novel method that automatically compiles natural language intents into editable and executable workflow graphs. The framework supports plug-in-based context integration, a reusable component library, and end-to-end visual interaction, significantly enhancing development efficiency and human-AI collaboration. Experimental evaluation across seven public benchmarks demonstrates that MASFactory accurately reproduces state-of-the-art multi-agent methodologies and validates the effectiveness of Vibe Graphing. The code and demonstration video are publicly available.

Technology Category

• Multiagent Systems: Multiagent Planning
• Intelligent Robots: Multi-Robot Systems
• Planning, Routing, and Scheduling: Planning with Language Models

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Economics, Online Markets and Human Computation: Architectures and workflows that use LLMs for crowd work

Abstract

Large language model-based (LLM-based) multi-agent systems (MAS) are increasingly used to extend agentic problem solving via role specialization and collaboration. MAS workflows can be naturally modeled as directed computation graphs, where nodes execute agents/sub-workflows and edges encode dependencies and message passing. However, implementing complex graph workflows in current frameworks still requires substantial manual effort, offers limited reuse, and makes it difficult to integrate heterogeneous external context sources. To overcome these limitations, we present MASFactory, a graph-centric framework for orchestrating LLM-based MAS. It introduces Vibe Graphing, a human-in-the-loop approach that compiles natural-language intent into an editable workflow specification and then into an executable graph. In addition, the framework provides reusable components and pluggable context integration, as well as a visualizer for topology preview, runtime tracing, and human-in-the-loop interaction. We evaluate MASFactory on seven public benchmarks, validating both reproduction consistency for representative MAS methods and the effectiveness of Vibe Graphing. Our code (https://github.com/BUPT-GAMMA/MASFactory) and video (https://youtu.be/ANynzVfY32k) are publicly available.

Problem

• LLM-based multi-agent systems
• workflow orchestration
• graph modeling
• context integration
• reusability

Innovation

• Vibe Graphing
• graph-centric orchestration
• LLM-based multi-agent systems
• human-in-the-loop workflow
• reusable MAS components