Reasoning and Planning with Dynamically Changing Norms

📰 ArXiv cs.AI

Learn to implement norm-guided planning in AI agents that interact with humans, considering dynamically changing norms

advanced Published 28 May 2026

Action Steps

Implement a defeasible calculus to resolve normative conflicts in AI planning
Integrate dynamically changing norms into the planning process using a human-AI setting
Use the approach to guide planning in AI agents that interact with humans
Test the system with various scenarios to ensure safe and norm-compliant interactions
Refine the system based on the results of the testing and evaluation

Who Needs to Know This

AI researchers and engineers working on human-AI interaction systems can benefit from this approach to ensure safe and norm-compliant interactions

Key Insight

💡 Dynamically changing norms must be considered in AI planning to ensure safe and norm-compliant human-AI interactions

Key Takeaways

Learn to implement norm-guided planning in AI agents that interact with humans, considering dynamically changing norms

Full Article

Title: Reasoning and Planning with Dynamically Changing Norms

Abstract:
arXiv:2605.27622v1 Announce Type: new 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

Read full paper → ← Back to Reads