Engaging in Dialogue about an Agent's Norms and Behaviors

TL;DR

This paper introduces a system enabling agents with moral and social norms in temporal logic to communicate and modify their norms through natural language, facilitating human-agent interaction and norm management.

Contribution

It presents a novel framework for natural language interaction with norm-based agent planning systems, including norm querying, addition, removal, and hypothetical scenario analysis.

Findings

Agents can respond to natural language queries about their norms.

Users can add or remove norms via natural language commands.

The system supports hypothetical norm modifications and their impact assessment.

Abstract

We present a set of capabilities allowing an agent planning with moral and social norms represented in temporal logic to respond to queries about its norms and behaviors in natural language, and for the human user to add and remove norms directly in natural language. The user may also pose hypothetical modifications to the agent's norms and inquire about their effects.