A Dual-Helix Governance Approach Towards Reliable Agentic AI for WebGIS Development
2026-03-04 • Artificial Intelligence
Artificial IntelligenceSoftware Engineering
AI summaryⓘ
The authors explain that building WebGIS tools with AI agents is hard because current language models have problems like forgetting and making random mistakes. They suggest a new system that treats these problems as governance issues, not just model limits. Their method uses a knowledge graph and a self-learning loop to help AI manage tasks more reliably. When tested on a big mapping tool, their system simplified the code and made it easier to maintain. They also show that good governance, not just smarter AI, improves reliability in geospatial software.
WebGISAgentic AILarge Language Models (LLM)Knowledge GraphGovernance FrameworkCyclomatic ComplexityMaintainability IndexModular CodeSelf-learning CycleGeospatial Engineering
Authors
Boyuan, Guan, Wencong Cui, Levente Juhasz
Abstract
WebGIS development requires rigor, yet agentic AI frequently fails due to five large language model (LLM) limitations: context constraints, cross-session forgetting, stochasticity, instruction failure, and adaptation rigidity. We propose a dual-helix governance framework reframing these challenges as structural governance problems that model capacity alone cannot resolve. We implement the framework as a 3-track architecture (Knowledge, Behavior, Skills) that uses a knowledge graph substrate to stabilize execution by externalizing domain facts and enforcing executable protocols, complemented by a self-learning cycle for autonomous knowledge growth. Applying this to the FutureShorelines WebGIS tool, a governed agent refactored a 2,265-line monolithic codebase into modular ES6 components. Results demonstrated a 51\% reduction in cyclomatic complexity and a 7-point increase in maintainability index. A comparative experiment against a zero-shot LLM confirms that externalized governance, not just model capability, drives operational reliability in geospatial engineering. This approach is implemented in the open-source AgentLoom governance toolkit.