Reasoning and Planning with Dynamically Changing Norms

Taylor Olson; Roberto Salas-Damian; Kenneth D Forbus

doi:10.48550/arxiv.2605.27622

Back

Reasoning and Planning with Dynamically Changing Norms

Preprint

Open access

Reasoning and Planning with Dynamically Changing Norms

Taylor Olson, Roberto Salas-Damian and Kenneth D Forbus

ArXiv.org

Cornell University

05/26/2026

DOI: 10.48550/arxiv.2605.27622

Files and links (1)

url

https://doi.org/10.48550/arxiv.2605.27622View

Preprint (Author's original) This preprint has not been evaluated by subject experts through peer review. Preprints may undergo extensive changes and/or become peer-reviewed journal articles. Open Access

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.

Computer Science - Artificial Intelligence

Computer Science - Symbolic Computation

Details

Title: Subtitle: Reasoning and Planning with Dynamically Changing Norms
Creators: Taylor Olson
Roberto Salas-Damian
Kenneth D Forbus
Resource Type: Preprint
Publication Details: ArXiv.org
DOI: 10.48550/arxiv.2605.27622
ISSN: 2331-8422
Publisher: Cornell University; Ithaca, New York
Language: English
Date posted: 05/26/2026
Academic Unit: Computer Science
Record Identifier: 9985167583202771

Metrics

1 Record Views