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

TL;DR

The paper presents COMPASS, a unified multi-agent framework that integrates sovereignty, sustainability, compliance, and ethics into autonomous systems, using RAG-augmented evaluations for explainability and real-time arbitration.

Contribution

It introduces a novel modular architecture combining specialized agents with RAG grounding and LLM-based judgment for multi-dimensional value alignment in autonomous AI.

Findings

RAG integration improves evaluation coherence and reduces hallucinations.

The framework enables real-time conflict arbitration among multiple ethical and regulatory dimensions.

COMPASS demonstrates adaptability across diverse application domains.

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.