PUBLICATION
Towards Governance-Aware Local and Hybrid AI Agents for Web Applications
Type
Conference Paper
Year
2026
Authors
Lucas Schröder M.Sc.
Prof. Dr.-Ing. Martin Gaedke
Research Area
Event
26th International Conference on Web Engineering
Published in
26th International Conference on Web Engineering, Lyon, France
ISBN/ISSN
tba
Download
Abstract
Governance of AI systems is becoming a critical issue as both societal and regulatory circumstances demand requirements such as safe information handling, transparency, and explainability. This is complicated by the widespread use of third-party-operated LLMs, which limits organizations' control over the embedding and enforcement of governance and organizational policies directly within the agent. Consequently, users are required to exercise caution or are prevented from using these agents when interacting with web applications that contain potentially sensitive information or require transparent and explainable processing. We propose a framework and architecture for embedding governance and organizational policies for data handling and explainability within web agents based on local, tool-calling small language models. This core will be expanded with governance-aware hybrid routing to remote LLMs for non-critical tasks, balancing the high capabilities of large, third-party provided systems with the safe and transparent environment established through local processing.
Reference
TBA
