Reasoning and Planning with Dynamically Changing Norms
Quick Take
This paper introduces a novel approach for AI agents to plan with dynamically changing human norms, using a defeasible calculus to resolve normative conflicts. The method is empirically validated with the SocialBot AI on a natural language dialogue task, demonstrating its effectiveness in real-world interactions.
Key Points
- Introduces a defeasible calculus for resolving normative conflicts in AI planning.
- Demonstrates the approach with SocialBot on a natural language dialogue task.
- Focuses on the dynamic nature of human norms in AI interactions.
- Aims to enhance safety in human-AI collaboration through norm-guided planning.
Article Excerpt
From source RSS / original summaryarXiv: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 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.
Reader Mode unavailable (could not extract clean content).
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.AI
See more →The Importance of Out-of-Band Metadata for Safe Autonomous Agents: The Redpanda Agentic Data Plane
The Redpanda Agentic Data Plane (ADP) introduces out-of-band metadata channels to enhance the safety of autonomous AI agents, ensuring secure data access and tamper-proof audit trails. This architecture mitigates risks associated with unpredictable AI behavior by enforcing governance throughout the agent lifecycle, demonstrated in a multi-agent trading system with strict data scoping and approval thresholds.