---
title: "MASFactory — paper by Liu et al. (2026) — summary and ideas"
description: "The authors present MASFactory, an open-source framework that represents workflows as Node/Edge graphs. 29 references."
authors: ["Yang Liu", "Jinxuan Cai", "Yishen Li", "Qi Meng", "Zedi Liu", "Xin Li", "Chen Qian", "Chuan Shi", "Cheng Yang"]
year: 2026
venue: "Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations)"
source: "https://aclanthology.org/2026.acl-demo.35/"
doi: "10.18653/v1/2026.acl-demo.35"
licence: "CC BY 4.0 (ACL Anthology)"
licence_url: "https://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/liu-2026-masfactory-graph-centric-framework-orchestrating/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/liu-2026-masfactory-graph-centric-framework-orchestrating/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2026](https://md.research.elamur.ai/free/en/papers/2026/page/36/) / MASFactory: A Graph-centric Framework for Orchestrating LLM-Based Multi-Agent Systems with Vibe Graphing

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

**Authors:** [Yang Liu](https://md.research.elamur.ai/free/en/authors/yang-liu/), Jinxuan Cai, Yishen Li, Qi Meng, Zedi Liu, [Xin Li](https://md.research.elamur.ai/free/en/authors/xin-li/), [Chen Qian](https://md.research.elamur.ai/free/en/authors/chen-qian/), [Chuan Shi](https://md.research.elamur.ai/free/en/authors/chuan-shi/) and [Cheng Yang](https://md.research.elamur.ai/free/en/authors/cheng-hong-yang/) · **Year:** 2026 · **Venue:** [Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations)](https://md.research.elamur.ai/free/en/venues/acl/) ([ACL 2026](https://md.research.elamur.ai/free/en/venues/acl/2026/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2026.acl-demo.35/) · [PDF](https://aclanthology.org/2026.acl-demo.35.pdf) · [DOI 10.18653/v1/2026.acl-demo.35](https://doi.org/10.18653/v1/2026.acl-demo.35) · [OpenAlex](https://openalex.org/W7166860154)

**Citations:** 0 citations (OpenAlex, 2026-10-14)

## Summary
Building LLM-based multi-agent systems (MAS) as directed graphs in tools like LangGraph or Dify still takes a lot of manual work. Developers must write role prompts, wire routing, and add custom glue code for memory, RAG, MCP or skills, and repeated subgraphs are hard to reuse. The authors present MASFactory, an open-source framework that represents workflows as Node/Edge graphs. Information moves through separate control, message and state flows, and a readiness-based scheduler can run ready nodes in parallel.

Its main feature is Vibe Graphing. A user describes the intended workflow in plain language, and the system works through three stages (role assignment, topology design, semantic completion), with the user able to review each one. The result is an editable intermediate specification, which is then compiled into an executable graph. A visualizer, reusable templates, multimodal messages and a pluggable Context Adapter complete the system.

On seven benchmarks, reproductions of five well-known MAS roughly match their original implementations, and the automatically generated workflows are competitive. This lowers the cost of MAS prototyping.

## Key points
- **Benchmarks and baselines:** evaluation covers HumanEval, MBPP, BigCodeBench, SRDD, MMLU-Pro, GAIA and GPQA. Reimplemented systems are ChatDev, MetaGPT, AgentVerse, CAMEL and HuggingGPT. Example: MetaGPT on HumanEval rises from 67.07 (original) to 89.02 (MASFactory).
- **Models:** workflows are built with gpt-5.2 and executed with gpt-4o-mini.
- **Code size for ChatDev:**
  - original workflow definition: 1,511 lines
  - MASFactory reproduction with ComposedGraph: 1,114 lines
  - Vibe Graphing-ChatDev: 203 lines
  - Vibe Graphing-Task Specific: 45 lines
- **Cost versus Vibe Coding:** Vibe Graphing costs about $0.26–0.59 compared with $3.02–6.08, roughly ten times cheaper. Vibe Coding graphs often contained logic errors, so they were left out of the accuracy comparison.
- **Components and availability:**
  - node types: Graph, Loop, Agent, CustomNode, Interaction, Switch
  - integrations: Mem0, LlamaIndex, MCP
  - code: github.com/BUPT-GAMMA/MASFactory, Apache-2.0
  - limitation: no built-in checkpointing for resuming interrupted runs.

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

## Institutions

- [Shanghai Jiao Tong University](https://md.research.elamur.ai/free/en/universities/shanghai-jiao-tong-university/) — University, Shanghai, China · 149 works · 16,161 citations
- [Beijing University of Posts and Telecommunications](https://md.research.elamur.ai/free/en/universities/beijing-university-of-posts-and-telecommunications/) — University, Beijing, China · 57 works · 32,843 citations

📚 Shelves (4): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 16,667 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 16,194 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 16,039 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 15,891 works

## Cite

Cite as: Yang Liu, Jinxuan Cai, Yishen Li, Qi Meng, Zedi Liu, Xin Li, Chen Qian, Chuan Shi and Cheng Yang. 2026. MASFactory: A Graph-centric Framework for Orchestrating LLM-Based Multi-Agent Systems with Vibe Graphing. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations).

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@inproceedings{liu2026masfactory,
  title = {{MASFactory: A Graph-centric Framework for Orchestrating LLM-Based Multi-Agent Systems with Vibe Graphing}},
  author = {Yang Liu, Jinxuan Cai, Yishen Li, Qi Meng, Zedi Liu, Xin Li, Chen Qian, Chuan Shi and Cheng Yang},
  booktitle = {Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations)},
  year = {2026},
  doi = {10.18653/v1/2026.acl-demo.35},
  url = {https://doi.org/10.18653/v1/2026.acl-demo.35}
}
```

- [← previous MASA: A Novel Multimodal Foundation Model for L2 Speaking Assessment in Picture-description Scenarios](https://md.research.elamur.ai/free/en/papers/yan-2026-masa-novel-multimodal-foundation-model/)
- [next → Mask-to-Correct+: Leveraging Retriever Diversity for Masking-guided Faithful Fact Correction](https://md.research.elamur.ai/free/en/papers/santra-2026-mask-correct-leveraging-retriever-diversity/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/36/)

## References

29 references, 18 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Anthropic. 2025a. Agent skills. [https://platform.claude.com/docs/en/agents-and-tools/](https://platform.claude.com/docs/en/agents-and-tools/) agent-skills/overview. Accessed: 2026-05-15. [↗](https://platform.claude.com/docs/en/agents-and-tools/)
2. Anthropic. 2025b. Model context protocol (MCP) specification. Accessed: 2026-02-23. [find](https://scholar.google.com/scholar?q=Anthropic%2E+2025b%2E+Model+context+protocol+%28MCP%29+specification%2E+Accessed%3A+2026%2D02%2D23%2E)
3. Jacob Austin, Augustus Odena, Maxwell Nye, Maarten Bosma, Henryk Michalewski, David Dohan, Ellen Jiang, Carrie Cai, Michael Terry, Quoc Le, and Charles Sutton. 2021. [Program synthesis with large language models](https://md.research.elamur.ai/free/en/papers/austin-2021-program-synthesis-large-language-models/). arXiv preprint arXiv:2108.07732.
4. Mark Chen, Jerry Tworek, Heewoo Jun, Qiming Yuan, Henrique Ponde de Oliveira Pinto, Jared Kaplan, Harri Edwards, Yuri Burda, Nicholas Joseph, Greg Brockman, Alex Ray, Raul Puri, Gretchen Krueger, Michael Petrov, Heidy Khlaaf, Girish Sastry, Pamela Mishkin, Brooke Chan, Scott Gray, and 39 others. 202… — [Evaluating Large Language Models Trained on Code](https://md.research.elamur.ai/free/en/papers/chen-2021-evaluating-large-language-models-trained/)
5. Weize Chen, Yusheng Su, Jingwei Zuo, Cheng Yang, Chenfei Yuan, Chi-Min Chan, Heyang Yu, Yaxi Lu, Yi-Hsin Hung, Chen Qian, Yujia Qin, Xin Cong, Ruobing Xie, Zhiyuan Liu, Maosong Sun, and Jie Zhou. 2024. [AgentVerse: Facilitating multi-agent collaboration and exploring emergent behaviors](https://md.research.elamur.ai/free/en/papers/chen-2023-agentverse-facilitating-multi-agent/). In The Twelft…
6. Prateek Chhikara, Dev Khant, Saket Aryan, Taranjeet Singh, and Deshraj Yadav. 2025. [Mem0: Building production-ready AI agents with scalable long-term memory](https://md.research.elamur.ai/free/en/papers/chhikara-2025-mem0-building-production-ready-ai/). Preprint, arXiv:2504.19413.
7. CrewAI Inc. 2024. CrewAI. Accessed: 2026-02-23. [find](https://scholar.google.com/scholar?q=CrewAI+Inc%2E+2024%2E+CrewAI%2E+Accessed%3A+2026%2D02%2D23%2E)
8. Darren Edge, Ha Trinh, Newman Cheng, Joshua Bradley, Alex Chao, Apurva Mody, Steven Truitt, Dasha Metropolitansky, Robert Osazuwa Ness, and Jonathan Larson. 2024. From local to global: A graph RAG approach to query-focused summarization. Preprint, arXiv:2404.16130. [find](https://scholar.google.com/scholar?q=Darren+Edge%2C+Ha+Trinh%2C+Newman+Cheng%2C+Joshua+Bradley%2C+Alex+Chao%2C+Apurva+Mody%2C+Steven+Truitt%2C+Dasha+Metropolitansky%2C+Robert+Osazuwa+Ness%2C+and+Jonathan+Larson%2E+2024%2E+From+local+to+global%3A+A+graph+RAG+app)
9. Google. 2024. Agent development kit (ADK). Accessed: 2026-02-23. [find](https://scholar.google.com/scholar?q=Google%2E+2024%2E+Agent+development+kit+%28ADK%29%2E+Accessed%3A+2026%2D02%2D23%2E)
10. Sirui Hong, Mingchen Zhuge, Jonathan Chen, Xiawu Zheng, Yuheng Cheng, Jinlin Wang, Ceyao Zhang, Zili Wang, Steven Ka Shing Yau, Zijuan Lin, Liyang Zhou, Chenyu Ran, Lingfeng Xiao, Chenglin Wu, and Jürgen Schmidhuber. 2024. [MetaGPT: Meta programming for a multi-agent collaborative framework](https://md.research.elamur.ai/free/en/papers/hong-2023-metagpt-meta-programming-multi/). In The T…
11. Jiazheng Kang, Mingming Ji, Zhe Zhao, and Ting Bai. 2025. [Memory OS of AI agent](https://md.research.elamur.ai/free/en/papers/kang-2025-memory-os-ai-agent/). In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing (EMNLP).
12. LangChain. 2024. LangGraph. Accessed: 2026-02-23. [find](https://scholar.google.com/scholar?q=LangChain%2E+2024%2E+LangGraph%2E+Accessed%3A+2026%2D02%2D23%2E)
13. LangGenius. 2024. Dify: An LLM app development platform. Accessed: 2026-02-23. [find](https://scholar.google.com/scholar?q=LangGenius%2E+2024%2E+Dify%3A+An+LLM+app+development+platform%2E+Accessed%3A+2026%2D02%2D23%2E)
14. Patrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni, Vladimir Karpukhin, Naman Goyal, Heinrich Küttler, Mike Lewis, Wen-tau Yih, Tim Rocktäschel, Sebastian Riedel, and Douwe Kiela. 2020. [Retrieval-augmented generation for knowledge-intensive NLP tasks](https://md.research.elamur.ai/free/en/papers/lewis-2020-retrieval-augmented-generation-knowledge-intensive/). In Advances in Neural Information Proc…
15. Guohao Li, Hasan Abed Al Kader Hammoud, Hani Itani, Dmitrii Khizbullin, and Bernard Ghanem. 2023. [CAMEL: Communicative agents for "mind" exploration of large language model society](https://md.research.elamur.ai/free/en/papers/li-2023-camel-communicative-agents-mind/). In Advances in Neural Information Processing Systems (NeurIPS).
16. Zijun Liu, Yanzhe Zhang, Peng Li, Yang Liu, and Diyi Yang. 2024. A dynamic LLM-powered agent network for task-oriented agent collaboration. In First Conference on Language Modeling (COLM). [find](https://scholar.google.com/scholar?q=Zijun+Liu%2C+Yanzhe+Zhang%2C+Peng+Li%2C+Yang+Liu%2C+and+Diyi+Yang%2E+2024%2E+A+dynamic+LLM%2Dpowered+agent+network+for+task%2Doriented+agent+collaboration%2E+In+First+Conference+on+Language+Modeling+%28COLM%29%2E)
17. LlamaIndex. 2024. LlamaIndex. Accessed: 2026-02-23. [find](https://scholar.google.com/scholar?q=LlamaIndex%2E+2024%2E+LlamaIndex%2E+Accessed%3A+2026%2D02%2D23%2E)
18. Grégoire Mialon, Clémentine Fourrier, Thomas Wolf, Yann LeCun, and Thomas Scialom. 2024. [GAIA: a benchmark for general AI assistants](https://md.research.elamur.ai/free/en/papers/mialon-2023-gaia-benchmark-general-ai-assistants/). In The Twelfth International Conference on Learning Representations (ICLR).
19. Charles Packer, Sarah Wooders, Kevin Lin, Vivian Fang, Shishir G. Patil, Ion Stoica, and Joseph E. Gonzalez. 2023. MemGPT: Towards LLMs as operating systems. Preprint, arXiv:2310.08560. [find](https://scholar.google.com/scholar?q=Charles+Packer%2C+Sarah+Wooders%2C+Kevin+Lin%2C+Vivian+Fang%2C+Shishir+G%2E+Patil%2C+Ion+Stoica%2C+and+Joseph+E%2E+Gonzalez%2E+2023%2E+MemGPT%3A+Towards+LLMs+as+operating+systems%2E+Preprint%2C+arXiv%3A2310%2E08560%2E)
20. Chen Qian, Wei Liu, Hongzhang Liu, Nuo Chen, Yufan Dang, Jiahao Li, Cheng Yang, Weize Chen, Yusheng Su, Xin Cong, Juyuan Xu, Dahai Li, Zhiyuan Liu, and Maosong Sun. 2024. [ChatDev: Communicative agents for software development](https://md.research.elamur.ai/free/en/papers/qian-2023-chatdev-communicative-agents-software/). In Proceedings of the 62nd Annual Meeting of the Association for Computat…
21. Noah Shinn, Federico Cassano, Ashwin Gopinath, Karthik Narasimhan, and Shunyu Yao. 2023. [Reflexion: Language agents with verbal reinforcement learning](https://md.research.elamur.ai/free/en/papers/shinn-2023-reflexion-language-agents-verbal-reinforcement/). In Advances in Neural Information Processing Systems (NeurIPS).
22. Yubo Wang, Xueguang Ma, Ge Zhang, Yuansheng Ni, Abhranil Chandra, Shiguang Guo, Weiming Ren, Aaran Arulraj, Xuan He, Ziyan Jiang, Tianle Li, Max Ku, Kai Wang, Alex Zhuang, Rongqi Fan, Xiang Yue, and Wenhu Chen. 2024. [MMLU-Pro: A more robust and challenging multi-task language understanding benchmark](https://md.research.elamur.ai/free/en/papers/wang-2024-mmlu-pro-more-robust-challenging/)…
23. Qingyun Wu, Gagan Bansal, Jieyu Zhang, Yiran Wu, Beibin Li, Erkang Zhu, Li Jiang, Xiaoyun Zhang, Shaokun Zhang, Jiale Liu, Ahmed Hassan Awadallah, Ryen W White, Doug Burger, and Chi Wang. 2023. [AutoGen: Enabling next-gen LLM applications via multi-agent conversation](https://md.research.elamur.ai/free/en/papers/wu-2023-autogen-enabling-next-gen-llm/). Preprint, arXiv:2308.08155.
24. Shunyu Yao, Jeffrey Zhao, Dian Yu, Nan Du, Izhak Shafran, Karthik R. Narasimhan, and Yuan Cao. 2023. [ReAct: Synergizing reasoning and acting in language models](https://md.research.elamur.ai/free/en/papers/yao-2022-react-synergizing-reasoning-acting-language/). In The Eleventh International Conference on Learning Representations (ICLR). OpenReview.net.
25. Mingchen Zhuge, Wenyi Wang, Louis Kirsch, Francesco Faccio, Dmitrii Khizbullin, and Jürgen Schmidhuber. 2024. GPTSwarm: Language agents as optimizable graphs. In Proceedings of the 41st International Conference on Machine Learning (ICML), pages 62743–62767. [find](https://scholar.google.com/scholar?q=Mingchen+Zhuge%2C+Wenyi+Wang%2C+Louis+Kirsch%2C+Francesco+Faccio%2C+Dmitrii+Khizbullin%2C+and+J%C3%BCrgen+Schmidhuber%2E+2024%2E+GPTSwarm%3A+Language+agents+as+optimizable+graphs%2E+In+Proceedings+of+the+41st+International+)
26. Terry Yue Zhuo, Minh Chien Vu, Jenny Chim, Han Hu, Wenhao Yu, Ratnadira Widyasari, Imam Nur Bani Yusuf, Haolan Zhan, Junda He, Indraneil Paul, Simon Brunner, Chen Gong, Thong Hoang, Armel Randy Zebaze, Xiaoheng Hong, Wen-Ding Li, Jean Kaddour, Ming Xu, Zhihan Zhang, and 14 others. 2025. [BigCodeBench…](https://md.research.elamur.ai/free/en/papers/zhuo-2024-bigcodebench-benchmarking-code-generation-diverse/)
27. David Rein, Betty Li Hou, Asa Cooper Stickland, Jackson Petty, Richard Yuanzhe Pang, Julien Dirani, Julian Michael, and Samuel R. Bowman. 2024. [GPQA: A graduate-level google-proof q&a benchmark](https://md.research.elamur.ai/free/en/papers/rein-2023-gpqa-graduate-level-google-proof/). In First Conference on Language Modeling (COLM).
28. Timo Schick, Jane Dwivedi-Yu, Roberto Dessì, Roberta Raileanu, Maria Lomeli, Eric Hambro, Luke Zettlemoyer, Nicola Cancedda, and Thomas Scialom. 2023. [Toolformer: Language models can teach themselves to use tools](https://md.research.elamur.ai/free/en/papers/schick-2023-toolformer-language-models-can-teach/). In Advances in Neural Information Processing Systems (NeurIPS).
29. Yongliang Shen, Kaitao Song, Xu Tan, Dongsheng Li, Weiming Lu, and Yueting Zhuang. 2023. [Hugginggpt: Solving ai tasks with chatgpt and its friends in hugging face](https://md.research.elamur.ai/free/en/papers/shen-2023-hugginggpt-solving-ai-tasks-chatgpt/). In Advances in Neural Information Processing Systems, pages 38154–38180. Curran Associates, Inc.

*Updated 1 November 2026*