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

Researchers propose a dual-helix governance framework to address AI agent reliability issues in WebGIS development, implementing a 3-track architecture that achieved 51% reduction in code complexity. The framework uses knowledge graphs and self-learning cycles to overcome LLM limitations like context constraints and instruction failures.

• →A dual-helix governance framework addresses five key LLM limitations in AI agent development including context constraints and cross-session forgetting.
• →The 3-track architecture (Knowledge, Behavior, Skills) uses knowledge graphs to externalize domain facts and enforce executable protocols.
• →Testing on FutureShorelines WebGIS tool showed 51% reduction in cyclomatic complexity and 7-point maintainability improvement.
• →Comparative experiments confirm that externalized governance, not just model capability, drives operational reliability.
• →The approach is implemented in the open-source AgentLoom governance toolkit for broader adoption.