English

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

Artificial Intelligence 2025-12-10 v1

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.

Keywords

Cite

@article{arxiv.2512.08536,
  title  = {Principles2Plan: LLM-Guided System for Operationalising Ethical Principles into Plans},
  author = {Tammy Zhong and Yang Song and Maurice Pagnucco},
  journal= {arXiv preprint arXiv:2512.08536},
  year   = {2025}
}

Comments

Accepted by AAAI 2026

R2 v1 2026-07-01T08:16:50.515Z