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

• URL: http://arxiv.org/abs/2603.15643v1
• Date: Tue, 03 Mar 2026 21:37:44 GMT
• Title: GSI Agent: Domain Knowledge Enhancement for Large Language Models in Green Stormwater Infrastructure
• Abstract summary: Green Stormwater Infrastructure (GSI) systems require continuous inspection and maintenance to ensure long-term performance.<n> domain knowledge about GSI is often scattered across municipal manuals, regulatory documents, and inspection forms.<n>We propose GSI Agent, a framework designed to improve performance in GSI-related tasks.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Green Stormwater Infrastructure (GSI) systems, such as permeable pavement, rain gardens, and bioretention facilities, require continuous inspection and maintenance to ensure long-term performance. However, domain knowledge about GSI is often scattered across municipal manuals, regulatory documents, and inspection forms. As a result, non-expert users and maintenance staff may struggle 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 improve 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 generation (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 remains stable (0.304 vs. 0.305). These results demonstrate that systematic domain knowledge enhancement can effectively adapt general-purpose LLMs to professional infrastructure applications.

Related papers

• From Insight to Action: A Novel Framework for Interpretability-Guided Data Selection in Large Language Models [73.72877445629383]
  Interpretability-Guided Data Selection (IGDS) is a framework that first identifies causal task features through frequency recall and interventional filtering.<n>We validate IGDS on mathematical reasoning, summarization, and translation tasks within Gemma-2, LLaMA-3.1, and Qwen3 models.
  arXiv  Detail & Related papers  (2026-04-28T03:16:24Z)
• GCA Framework: A GCC Countries-Grounded Dataset and Agentic Pipeline for Climate Decision Support [67.9633930125889]
  We present the GCA framework, which unifies (i) GCA-DS, a curated multimodal dataset grounded in the GCC states, and (ii) Gulf Climate Agent (GCA), a tool-augmented agent for climate analysis.<n>GCA-DS comprises 200k question--answer pairs spanning governmental policies and adaptation plans, NGO and international frameworks, academic, literature, and event-driven reporting on heatwaves, dust storms, and floods.<n>GCA agent orchestrates a modular tool pipeline grounded in real-time and historical signals and geospatial processing that produces derived indices and interpretable visualizations.
  arXiv  Detail & Related papers  (2026-04-14T05:31:40Z)
• Why Does the LLM Stop Computing: An Empirical Study of User-Reported Failures in Open-Source LLMs [50.075587392477935]
  We conduct the first large-scale empirical study of 705 real-world failures from the open-source DeepSeek, Llama, and Qwen ecosystems.<n>Our analysis reveals a paradigm shift: white-box orchestration relocates the reliability bottleneck from model algorithmic defects to the systemic fragility of the deployment stack.
  arXiv  Detail & Related papers  (2026-01-20T06:42:56Z)
• Unleashing the Capabilities of Large Vision-Language Models for Intelligent Perception of Roadside Infrastructure [12.667510244197047]
  General-purpose models often struggle to capture the necessary fine-grained attributes and domain rules.<n>We propose a domain-adapted framework that transforms Large Vision Language Models into specialized agents for intelligent infrastructure analysis.<n>Our framework achieves a detection performance of 58.9 mAP and an attribute recognition accuracy of 95.5%.
  arXiv  Detail & Related papers  (2026-01-15T16:16:34Z)
• KEO: Knowledge Extraction on OMIn via Knowledge Graphs and RAG for Safety-Critical Aviation Maintenance [43.78384523553438]
  We present a domain-specific knowledge extraction and reasoning framework with large language models (LLMs) in safety-critical contexts.<n>Using the Operations and Maintenance Intelligence (OMIn) dataset, we construct a QA benchmark spanning global sensemaking and actionable maintenance tasks.<n>Experiments show that KEO markedly improves global sensemaking by revealing patterns and system-level insights, while text-chunk RAG remains effective for fine-grained procedural tasks.
  arXiv  Detail & Related papers  (2025-10-07T02:29:13Z)
• GRE Suite: Geo-localization Inference via Fine-Tuned Vision-Language Models and Enhanced Reasoning Chains [20.788130896943663]
  Geo Reason Enhancement (GRE) Suite is a novel framework that augments Visual Language Models with structured reasoning chains for interpretable location inference.<n>First, we introduce GRE30K, a high-quality geo-localization reasoning dataset designed to facilitate fine-grained visual and contextual analysis.<n>Next, we present the GRE model, which employs a multi-stage reasoning strategy to progressively infer scene attributes, local details, and semantic features, thereby narrowing down potential geographic regions with enhanced precision.
  arXiv  Detail & Related papers  (2025-05-24T13:48:57Z)
• DO-RAG: A Domain-Specific QA Framework Using Knowledge Graph-Enhanced Retrieval-Augmented Generation [4.113142669523488]
  Domain-specific QA systems require generative fluency but high factual accuracy grounded in structured expert knowledge.<n>We propose DO-RAG, a scalable and customizable hybrid QA framework that integrates multi-level knowledge graph construction with semantic vector retrieval.
  arXiv  Detail & Related papers  (2025-05-17T06:40:17Z)
• Enhancing Large Language Models (LLMs) for Telecommunications using Knowledge Graphs and Retrieval-Augmented Generation [52.8352968531863]
  Large language models (LLMs) have made significant progress in general-purpose natural language processing tasks.<n>This paper presents a novel framework that combines knowledge graph (KG) and retrieval-augmented generation (RAG) techniques to enhance LLM performance in the telecom domain.
  arXiv  Detail & Related papers  (2025-03-31T15:58:08Z)
• GEOBench-VLM: Benchmarking Vision-Language Models for Geospatial Tasks [84.86699025256705]
  We present GEOBench-VLM, a benchmark specifically designed to evaluate Vision-Language Models (VLMs) on geospatial tasks.<n>Our benchmark features over 10,000 manually verified instructions and spanning diverse visual conditions, object types, and scales.<n>We evaluate several state-of-the-art VLMs to assess performance on geospatial-specific challenges.
  arXiv  Detail & Related papers  (2024-11-28T18:59:56Z)
• FederatedScope-GNN: Towards a Unified, Comprehensive and Efficient Package for Federated Graph Learning [65.48760613529033]
  Federated graph learning (FGL) has not been well supported due to its unique characteristics and requirements. We first discuss the challenges in creating an easy-to-use FGL package and accordingly present our implemented package FederatedScope-GNN (FS-G) We validate the effectiveness of FS-G by conducting extensive experiments, which simultaneously gains many valuable insights about FGL for the community.
  arXiv  Detail & Related papers  (2022-04-12T06:48:06Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.