Overview
Field: AI Authors: Taylor Olson, Roberto Salas-Damian, Kenneth D. Forbus Published: 2026-05-28 arXiv: 2605.27622
Abstract (translated from the original)
To safely interact with humans, AI agents must both know our norms and consider them during planning. However, such norm-guided planning has been less explored, only within communities of artificial agents, and has ignored the dynamic nature of norms. This paper instead presents an approach to guiding planning with dynamically changing norms in a human-AI setting. We contribute a defeasible calculus for resolving normative conflicts and an approach to using such dynamically changing norms as guard rails on plans. We theoretically demonstrate our approach with formal proofs and empirically with an AI agent, SocialBot, on a natural language dialogue task.
Key Contributions
- A defeasible calculus for resolving normative conflicts that arise during planning.
- A method for using dynamically changing norms as guard rails on plans in human-AI interaction settings.
- Formal proofs providing theoretical guarantees for the approach.
- Empirical evaluation via SocialBot, an AI agent tested on a natural language dialogue task.
Original Abstract
To safely interact with humans, AI agents must both know our norms and consider them during planning. However, such norm-guided planning has been less explored, only within communities of artificial agents, and has ignored the dynamic nature of norms. This paper instead presents an approach to guiding planning with dynamically changing norms in a human-AI setting. We contribute a defeasible calculus for resolving normative conflicts and an approach to using such dynamically changing norms as guard rails on plans. We theoretically demonstrate our approach with formal proofs and empirically with an AI agent, SocialBot, on a natural language dialogue task.
---
Paper link: arXiv:2605.27622