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

arXiv: https://arxiv.org/abs/2501.17258 · HTML: https://mlsanity.com/paper/2501.17258/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Jan 2025.

## Built on by (most cited first, 12 of 12)

- [Characterizing LLM-driven Social Network: The Chirper.ai Case](https://mlsanity.com/paper/2504.10286/) (2025)
- [Multi-Party Conversational Agents: A Survey](https://mlsanity.com/paper/2505.18845/) (2025)
- [ProMediate: A Socio-cognitive framework for evaluating proactive agents in multi-party negotiation](https://mlsanity.com/paper/2510.25224/) (2025)
- [MURMUR: Using cross-user chatter to break collaborative language agents in groups](https://mlsanity.com/paper/2511.17671/) (2025)
- [Botender: Supporting Communities in Collaboratively Designing AI Agents through Case-Based Provocations](https://mlsanity.com/paper/2509.25492/) (2025)
- [Human-Human-AI Triadic Programming: Uncovering the Role of AI Agent and the Value of Human Partner in Collaborative Learning](https://mlsanity.com/paper/2601.12134/) (2026)
- [Computer Vision for Objects used in Group Work: Challenges and Opportunities](https://mlsanity.com/paper/2507.00224/) (2025)
- [Exploring Teachers' Perspectives on Using Conversational AI Agents for Group Collaboration](https://mlsanity.com/paper/2602.07142/) (2026)
- [The Triadic Loop: A Framework for Negotiating Alignment in AI Co-hosted Livestreaming](https://mlsanity.com/paper/2604.18850/) (2026)
- [TIDES: A Longitudinal Bilingual Dataset for Modeling Multi-Party Social Dynamics](https://mlsanity.com/paper/2608.01724/) (2026)
- [Live Assistant: Learning Whether, When, and Whom to Assist in Real-World Live Social Streams](https://mlsanity.com/paper/2609.27303/) (2026)
- [LLMs are General Asynchronous Agents](https://mlsanity.com/paper/2609.35427/) (2026)

## Abstract (arXiv)

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.