GSI Agent: Domain Knowledge Enhancement for Large Language Models in Green Stormwater Infrastructure

Computer Science > Artificial Intelligence [Submitted on 3 Mar 2026] GSI Agent: Domain Knowledge Enhancement for Large Language Models in Green Stormwater Infrastructure Shaohuang Wang Green Stormwater Infrastructure (GSI) systems, such as permeable pavement, rain gardens, and bioretention facilities, require continuous inspection and maintenance to ensure long-term perfor- mance. However, domain knowledge about GSI is often scattered across municipal manuals, regula- tory documents, and inspection forms. As a result, non-expert users and maintenance staff may strug- gle to obtain reliable and actionable guidance from field observations. Although Large Language Models (LLMs) have demonstrated strong general reasoning and language generation capabilities, they often lack domain-specific knowledge and may produce inaccurate or hallucinated answers in engineering scenarios. This limitation restricts their direct application to professional infrastructure tasks. In this paper, we propose GSI Agent, a domain-enhanced LLM framework designed to im- prove performance in GSI-related tasks. Our approach integrates three complementary strategies: (1) supervised fine-tuning (SFT) on a curated GSI instruction dataset, (2) retrieval-augmented gen- eration (RAG) over an internal GSI knowledge base constructed from municipal documents, and (3) an agent-based reasoning pipeline that coordinates retrieval, context integration, and structured response generation. We also construct a new GSI Dataset aligned with real-world GSI inspection and maintenance scenarios. Experimental results show that our framework significantly improves domain-specific performance while maintaining general knowledge capability. On the GSI dataset, BLEU-4 improves from 0.090 to 0.307, while performance on the common knowledge dataset re- mains stable (0.304 vs. 0.305). These results demonstrate that systematic domain knowledge en- hancement can effectively adapt general-purpose LLMs to professional infrastructure applications. Subjects: Artificial Intelligence (cs.AI) Cite as: arXiv:2603.15643 [cs.AI]   (or arXiv:2603.15643v1 [cs.AI] for this version)   https://doi.org/10.48550/arXiv.2603.15643 Focus to learn more Submission history From: Shaohuang Wang [view email] [v1] Tue, 3 Mar 2026 21:37:44 UTC (1,257 KB) Access Paper: HTML (experimental) view license Current browse context: cs.AI < prev   |   next > new | recent | 2026-03 Change to browse by: cs References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)