COMPASS: The explainable agentic framework for Sovereignty, Sustainability, Compliance, and Ethics

2026-03-11

AI Summary

This work addresses the lack of unified governance in existing large language model (LLM) agents concerning digital sovereignty, environmental sustainability, compliance, and ethics, which hinders their ability to jointly optimize these multidimensional value objectives. We propose the first multi-agent framework that integrates all four dimensions into a unified, interpretable architecture, comprising a central coordinator and four specialized sub-agents—each dedicated to sovereignty, carbon-aware computation, compliance, and ethics, respectively. By incorporating retrieval-augmented generation (RAG) and an LLM-as-a-judge mechanism, the framework enables real-time arbitration of conflicting objectives and supports modular extensibility. Experimental results demonstrate that our approach significantly enhances semantic consistency, reduces hallucination risks, and achieves strong cross-domain integrability, decision interpretability, and traceability.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Multiagent Systems: Mechanism Design
• Philosophy and Ethics of AI: Safety, Robustness & Trustworthiness

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Agentic search
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems

Abstract

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.

Problem

• digital sovereignty
• environmental sustainability
• regulatory compliance
• ethical alignment
• autonomous agents

Innovation

• COMPASS framework
• Retrieval-Augmented Generation (RAG)
• LLM-as-a-judge
• multi-agent orchestration
• value-aligned AI