LLM learns to facilitate group tasks with less friction and more comfort
Learning to GUIDE the Group: Self-Learning LLM Facilitation Across Multi-Party Tasks
Artificial Intelligence
Summary
Facilitating group conversations is hard because different people and tasks require different approaches. The authors created a method where a large language model (LLM) learns how to guide group discussions by studying many example talks led by expert LLM facilitators. This new model can help groups work better and feel more comfortable while using fewer words and turns to keep the conversation smooth. Their tests show this approach works well across different kinds of tasks without needing to be retrained for each one.
What this means in practice
- •For remote work teams: Use a single AI facilitator that adapts to diverse meeting types, improving comfort and reducing friction without needing task-specific setup.
- •For customer support centers: Deploy AI agents that can guide group problem-solving using learned general strategies that work across different customer issues.
Authors
Ziyi Liu, Tzu-Sheng Kuo, Jiale Liu, Deqing Fu, Nithum Thain, Crystal Qian
Abstract
As large language models are increasingly adopted as multi-party communication facilitators, there is a growing demand for agents capable of balancing diverse group dynamics across contexts. However, existing LLM facilitators are often fine-tuned for task-specific objectives; generalized LLM-based facilitation methods that can adapt to different types of tasks and diverse group dynamics are underdeveloped. To address this gap, we present GUIDE (Generalized Unified Intervention for Dynamic Exchanges, a framework for developing generalized LLM-based facilitators across different multi-party contexts. GUIDE evaluates facilitation across both objective task outcomes and subjective metrics, including psychological safety and perceived friction. Within this framework, we study whether LLMs can self-learn generalized facilitation strategy offline to real-time interventions. We first collect multi-party human interactions guided by task-specific expert LLM facilitators (N=432 conversations). We then employ a self-learning method in which an LLM induces an actionable strategic playbook from conversations and iteratively refines it using feedback from an LLM judge aligned with human annotators (N=20), developing a single generalized facilitator that outperforms the three task-specific expert facilitators on held-out conversations 61.4% win rate. Finally, we evaluate these improvements empirically; in a real-time online empirical study, the self-learned generalized facilitator preserves facilitator performance and group productivity, improves speaking comfort and reduces interpersonal friction, while using 24.7% fewer turns and 29.0% fewer words than the expert prompts. These findings provide empirical evidence that LLMs can learn generalizable, task-agnostic social facilitation from task-specific human interactions, on-par with hand-crafted task-specific prompts across diverse group settings.