Controlling AI Agent Participation in Group Conversations: A Human-Centered Approach

TL;DR

This paper explores how to design conversational AI agents for group settings, focusing on user preferences, control mechanisms, and developing a taxonomy to guide AI behavior in multi-user interactions.

Contribution

It introduces a taxonomy of controls for AI participation in group conversations, based on user studies and validation of control mechanisms.

Findings

Participants preferred AI in group but disliked dominance.

Controls over AI behavior improved user experience.

Developed a taxonomy to guide AI design in group interactions.

Abstract

Conversational AI agents are commonly applied within single-user, turn-taking scenarios. The interaction mechanics of these scenarios are trivial: when the user enters a message, the AI agent produces a response. However, the interaction dynamics are more complex within group settings. How should an agent behave in these settings? We report on two experiments aimed at uncovering users' experiences of an AI agent's participation within a group, in the context of group ideation (brainstorming). In the first study, participants benefited from and preferred having the AI agent in the group, but participants disliked when the agent seemed to dominate the conversation and they desired various controls over its interactive behaviors. In the second study, we created functional controls over the agent's behavior, operable by group members, to validate their utility and probe for additional requirements. Integrating our findings across both studies, we developed a taxonomy of controls for when, what, and where a conversational AI agent in a group should respond, who can control its behavior, and how those controls are specified and implemented. Our taxonomy is intended to aid AI creators to think through important considerations in the design of mixed-initiative conversational agents.