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

TL;DR

MASFactory is a graph-centric framework that simplifies the creation and management of large language model-based multi-agent systems through a human-in-the-loop approach called Vibe Graphing, enabling easier workflow specification and integration.

Contribution

It introduces Vibe Graphing for translating natural language into executable multi-agent workflows and provides reusable components, multimodal messaging, and visualization tools.

Findings

Validated on seven public benchmarks for consistency and effectiveness.

Demonstrated ease of workflow specification via human-in-the-loop Vibe Graphing.

Achieved reproducibility and integration capabilities in MAS workflows.

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 or 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, skill support, multimodal message handling, 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, licensed under Apache-2.0) and video demonstration (https://youtu.be/ANynzVfY32k) are publicly available.