Saved in:
Bibliographic Details
Main Authors: Xu, Haowen, Tupayachi, Jose, Yu, Xiao-Ying
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2511.20656
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912729350012928
author Xu, Haowen
Tupayachi, Jose
Yu, Xiao-Ying
author_facet Xu, Haowen
Tupayachi, Jose
Yu, Xiao-Ying
contents The development of web-based geospatial dashboards for risk analysis and decision support is often challenged by the difficulty in visualization of big, multi-dimensional environmental data, implementation complexity, and limited automation. We introduce a generative AI framework that harnesses Large Language Models (LLMs) to automate the creation of interactive geospatial dashboards from user-defined inputs including UI wireframes, requirements, and data sources. By incorporating a structured knowledge graph, the workflow embeds domain knowledge into the generation process and enable accurate and context-aware code completions. A key component of our approach is the Context-Aware Visual Prompting (CAVP) mechanism, which extracts encodes and interface semantics from visual layouts to guide LLM driven generation of codes. The new framework also integrates a self-validation mechanism that uses an agent-based LLM and Pass@k evaluation alongside semantic metrics to assure output reliability. Dashboard snippets are paired with data visualization codebases and ontological representations, enabling a pipeline that produces scalable React-based completions using the MVVM architectural pattern. Our results demonstrate improved performance over baseline approaches and expanded functionality over third party platforms, while incorporating multi-page, fully functional interfaces. We successfully developed a framework to implement LLMs, demonstrated the pipeline for automated code generation, deployment, and performed chain-of-thought AI agents in self-validation. This integrative approach is guided by structured knowledge and visual prompts, providing an innovative geospatial solution in enhancing risk analysis and decision making.
format Preprint
id arxiv_https___arxiv_org_abs_2511_20656
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Context-Aware Visual Prompting: Automating Geospatial Web Dashboards with Large Language Models and Agent Self-Validation for Decision Support
Xu, Haowen
Tupayachi, Jose
Yu, Xiao-Ying
Human-Computer Interaction
Artificial Intelligence
The development of web-based geospatial dashboards for risk analysis and decision support is often challenged by the difficulty in visualization of big, multi-dimensional environmental data, implementation complexity, and limited automation. We introduce a generative AI framework that harnesses Large Language Models (LLMs) to automate the creation of interactive geospatial dashboards from user-defined inputs including UI wireframes, requirements, and data sources. By incorporating a structured knowledge graph, the workflow embeds domain knowledge into the generation process and enable accurate and context-aware code completions. A key component of our approach is the Context-Aware Visual Prompting (CAVP) mechanism, which extracts encodes and interface semantics from visual layouts to guide LLM driven generation of codes. The new framework also integrates a self-validation mechanism that uses an agent-based LLM and Pass@k evaluation alongside semantic metrics to assure output reliability. Dashboard snippets are paired with data visualization codebases and ontological representations, enabling a pipeline that produces scalable React-based completions using the MVVM architectural pattern. Our results demonstrate improved performance over baseline approaches and expanded functionality over third party platforms, while incorporating multi-page, fully functional interfaces. We successfully developed a framework to implement LLMs, demonstrated the pipeline for automated code generation, deployment, and performed chain-of-thought AI agents in self-validation. This integrative approach is guided by structured knowledge and visual prompts, providing an innovative geospatial solution in enhancing risk analysis and decision making.
title Context-Aware Visual Prompting: Automating Geospatial Web Dashboards with Large Language Models and Agent Self-Validation for Decision Support
topic Human-Computer Interaction
Artificial Intelligence
url https://arxiv.org/abs/2511.20656