COMPASS: The explainable agentic framework for Sovereignty, Sustainability, Compliance, and Ethics
This addresses the problem of fragmented governance in autonomous AI systems for developers and organizations, though it appears incremental as it builds on existing methods like RAG and multi-agent architectures.
The paper tackles the challenge of integrating digital sovereignty, sustainability, compliance, and ethics into LLM-based agentic systems by introducing the COMPASS Framework, a multi-agent orchestration system that uses RAG and LLM-as-a-judge to assign scores and generate explainable justifications, with validation showing improved semantic coherence and reduced hallucination risks.
The rapid proliferation of large language model (LLM)-based agentic systems raises critical concerns regarding digital sovereignty, environmental sustainability, regulatory compliance, and ethical alignment. Whilst existing frameworks address individual dimensions in isolation, no unified architecture systematically integrates these imperatives into the decision-making processes of autonomous agents. This paper introduces the COMPASS (Compliance and Orchestration for Multi-dimensional Principles in Autonomous Systems with Sovereignty) Framework, a novel multi-agent orchestration system designed to enforce value-aligned AI through modular, extensible governance mechanisms. The framework comprises an Orchestrator and four specialised sub-agents addressing sovereignty, carbon-aware computing, compliance, and ethics, each augmented with Retrieval-Augmented Generation (RAG) to ground evaluations in verified, context-specific documents. By employing an LLM-as-a-judge methodology, the system assigns quantitative scores and generates explainable justifications for each assessment dimension, enabling real-time arbitration of conflicting objectives. We validate the architecture through automated evaluation, demonstrating that RAG integration significantly enhances semantic coherence and mitigates the hallucination risks. Our results indicate that the framework's composition-based design facilitates seamless integration into diverse application domains whilst preserving interpretability and traceability.