ArchiDocGen: Multi-Agent Framework for Expository Document Generation in the Architectural Industry
Junjie Jiang, Haodong Wu, Yongqi Zhang, Songyue Guo, Bingcen Liu, Caleb Chen Cao, Ruizhe Shao, Chao Guan, Peng Xu, Lei Chen
Abstract
The architectural industry produces extensive documents, including method statements—expository documents that integrate multi-source data into actionable guidance. Manual drafting however is labor-intensive and time-consuming. This paper introduces ArchiDocGen, a multi-agent framework automating method statement generation. Unlike traditional approaches relying on static templates or single-pass generation, ArchiDocGen decomposes the task into three steps: outline generation, section-based content generation, and polishing, each handled by specialized agents. To provide domain expertise, ArchiDocGen employs a section-based retriever to fetch and synthesize relevant documents from its custom knowledge base. Each section is generated through iterative reasoning of a section-based chain-of-thought (SeCoT) scheme, followed by refinement to meet professional standards. To evaluate the generated method statements, we partner with the industry to establish a multi-dimensional evaluation system by combining automatic and empirical methods. Experiments show that ArchiDocGen achieves 4.38 ContentScore, excelling in specialization, completeness, organization, and clarity. Additionally, a web-based application for ArchiDocGen is developed and deployed with industry partners.- Anthology ID:
- 2025.acl-industry.43
- Volume:
- Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 6: Industry Track)
- Month:
- July
- Year:
- 2025
- Address:
- Vienna, Austria
- Editors:
- Georg Rehm, Yunyao Li
- Venue:
- ACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 605–618
- Language:
- URL:
- https://preview.aclanthology.org/display_plenaries/2025.acl-industry.43/
- DOI:
- Cite (ACL):
- Junjie Jiang, Haodong Wu, Yongqi Zhang, Songyue Guo, Bingcen Liu, Caleb Chen Cao, Ruizhe Shao, Chao Guan, Peng Xu, and Lei Chen. 2025. ArchiDocGen: Multi-Agent Framework for Expository Document Generation in the Architectural Industry. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 6: Industry Track), pages 605–618, Vienna, Austria. Association for Computational Linguistics.
- Cite (Informal):
- ArchiDocGen: Multi-Agent Framework for Expository Document Generation in the Architectural Industry (Jiang et al., ACL 2025)
- PDF:
- https://preview.aclanthology.org/display_plenaries/2025.acl-industry.43.pdf