Mutual Theory of Mind in Human-AI Collaboration: An Empirical Study with LLM-driven AI Agents in a Real-time Shared Workspace Task
This work addresses the design of AI agents for real-time human collaboration, but it is incremental as it provides empirical insights without major breakthroughs.
The study investigated the impact of Mutual Theory of Mind (MToM) in human-AI collaboration using an LLM-driven AI agent in a real-time shared workspace task, finding that the agent's Theory of Mind capability did not significantly improve team performance but enhanced human understanding and the feeling of being understood, while bidirectional communication led to lower performance.
Theory of Mind (ToM) significantly impacts human collaboration and communication as a crucial capability to understand others. When AI agents with ToM capability collaborate with humans, Mutual Theory of Mind (MToM) arises in such human-AI teams (HATs). The MToM process, which involves interactive communication and ToM-based strategy adjustment, affects the team's performance and collaboration process. To explore the MToM process, we conducted a mixed-design experiment using a large language model-driven AI agent with ToM and communication modules in a real-time shared-workspace task. We find that the agent's ToM capability does not significantly impact team performance but enhances human understanding of the agent and the feeling of being understood. Most participants in our study believe verbal communication increases human burden, and the results show that bidirectional communication leads to lower HAT performance. We discuss the results' implications for designing AI agents that collaborate with humans in real-time shared workspace tasks.