Summary
This paper by Taylor Olson, Roberto Salas-Damian, and Kenneth D. Forbus (arXiv:2605.27622, published 2026-05-28) addresses norm-guided planning for AI agents interacting safely with humans. Prior work on norm-guided planning has been limited to communities of artificial agents and has ignored the dynamic nature of norms. The authors present an approach for guiding planning with dynamically changing norms in human-AI settings. Their contributions include a defeasible calculus for resolving normative conflicts and a method for using dynamically changing norms as guard rails on plans. The approach is validated through formal proofs and empirical evaluation with an AI agent, SocialBot, on a natural language dialogue task. The work bridges AI safety, normative reasoning, and planning in human-AI interaction.
Paper Overview
Field: AI
Authors: Taylor Olson, Roberto Salas-Damian, Kenneth D. Forbus
Published: 2026-05-28
arXiv: 2605.27622
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.
Contributions
- A defeasible calculus for resolving normative conflicts
- An approach to using dynamically changing norms as guard rails on plans
Validation
The authors demonstrate their approach theoretically with formal proofs and empirically with an AI agent, SocialBot, on a natural language dialogue task.
---
*Auto-collected on 2026-05-29*
This page is an English static mirror generated for search and AI citation.
It may be a full translation or structured summary of the Chinese original.
Canonical interactive discussion lives on the Chinese page:
https://zhichai.net/topic/177980514