Research

A Dual-Helix Governance Approach Towards Reliable Agentic AI for WebGIS Development

arXiv•March 4, 2026 ()• Boyuan, Guan, Wencong Cui, Levente Juhasz

Professional Abstract

"The research paper titled 'WebGIS Development and Agentic AI: Addressing Limitations through a Dual-Helix Governance Framework' presents a critical examination of the challenges faced in the development of WebGIS systems when utilizing large language models (LLMs). The authors identify five significant limitations of LLMs that hinder their effectiveness in agentic AI applications: context constraints, cross-session forgetting, stochasticity, instruction failure, and adaptation rigidity. These limitations are framed as structural governance problems that cannot be resolved solely through enhancements in model capacity. To address these challenges, the authors propose a novel dual-helix governance framework that is operationalized through a three-track architecture comprising Knowledge, Behavior, and Skills. This architecture leverages a knowledge graph substrate to stabilize execution by externalizing domain-specific facts and enforcing executable protocols, thereby enhancing the reliability of agentic AI systems in geospatial engineering tasks. The implementation of this framework is exemplified through the FutureShorelines WebGIS tool, where a governed agent was able to refactor a substantial 2,265-line monolithic codebase into modular ES6 components. This refactoring process yielded significant improvements in software quality, evidenced by a 51% reduction in cyclomatic complexity and a 7-point increase in the maintainability index. Furthermore, the study includes a comparative experiment against a zero-shot LLM, which underscores the importance of externalized governance mechanisms in achieving operational reliability, rather than relying solely on the capabilities of the model itself. The findings highlight that the proposed governance framework not only enhances the performance of agentic AI in WebGIS development but also contributes to the broader discourse on the integration of AI technologies in complex engineering domains. The approach is made accessible through the open-source AgentLoom governance toolkit, which aims to facilitate the adoption of these governance strategies in future AI-driven projects."

Technical Insights

1Identification of five critical limitations of large language models (LLMs) in agentic AI applications: context constraints, cross-session forgetting, stochasticity, instruction failure, and adaptation rigidity.

2Introduction of a dual-helix governance framework that reframes LLM limitations as structural governance problems.

3Implementation of a three-track architecture (Knowledge, Behavior, Skills) to enhance the operational reliability of WebGIS systems.

4Utilization of a knowledge graph substrate to externalize domain facts and enforce executable protocols, stabilizing execution in complex tasks.

5Case study on the FutureShorelines WebGIS tool demonstrating the practical application of the governance framework.

6Successful refactoring of a 2,265-line monolithic codebase into modular ES6 components, showcasing improved software design practices.

7Quantitative results indicating a 51% reduction in cyclomatic complexity and a 7-point increase in the maintainability index post-refactoring.

8Comparative analysis against a zero-shot LLM, emphasizing the role of externalized governance in driving operational reliability.

9Release of the open-source AgentLoom governance toolkit to promote the adoption of the proposed governance strategies in AI-driven engineering projects.