Principles2Plan: LLM-Guided System for Operationalising Ethical Principles into Plans

2025-12-09

AI Summary

Existing automated planning tools lack systematic support for ethical constraints in human environments; manually encoding ethical rules is costly and poorly generalizable. Method: We propose a human-in-the-loop framework that, for the first time, leverages large language models (LLMs) to automatically translate high-level ethical principles (e.g., beneficence, privacy) into executable, verifiable operators within classical planning formalisms. The framework integrates LLM-based semantic reasoning with symbolic planning’s interpretability, enabling interactive user review, prioritization, and deployment of generated rules through a closed-loop pipeline: rule generation → formal verification → plan execution. Contribution/Results: Our prototype system demonstrates efficient generation of ethically compliant plans in realistic scenarios. Empirical evaluation shows significant improvement in rule construction efficiency—reducing manual effort by up to 78%—and establishes the first principled approach to ethics-aware automated planning, thereby bridging a critical research gap.

Technology Category

• Humans and AI: Human-Aware Planning and Behavior Prediction
• Planning, Routing, and Scheduling: Planning with Language Models
• 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
• Economics, Online Markets and Human Computation: Fairness and ethical considerations in crowd work and in human-in-the-loop AI systems
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Ethical awareness is critical for robots operating in human environments, yet existing automated planning tools provide little support. Manually specifying ethical rules is labour-intensive and highly context-specific. We present Principles2Plan, an interactive research prototype demonstrating how a human and a Large Language Model (LLM) can collaborate to produce context-sensitive ethical rules and guide automated planning. A domain expert provides the planning domain, problem details, and relevant high-level principles such as beneficence and privacy. The system generates operationalisable ethical rules consistent with these principles, which the user can review, prioritise, and supply to a planner to produce ethically-informed plans. To our knowledge, no prior system supports users in generating principle-grounded rules for classical planning contexts. Principles2Plan showcases the potential of human-LLM collaboration for making ethical automated planning more practical and feasible.

Problem

• Operationalizing ethical principles into automated planning rules.
• Addressing lack of ethical support in existing robotic planning tools.
• Reducing manual labor in context-specific ethical rule specification.

Innovation

• LLM-human collaboration generates ethical rules
• System operationalizes high-level principles into plans
• Interactive prototype enables context-sensitive rule creation