pith. sign in

arxiv: 2409.08811 · v1 · pith:5HFE2FAU · submitted 2024-09-13 · cs.HC · cs.AI· cs.MA

Mutual Theory of Mind in Human-AI Collaboration: An Empirical Study with LLM-driven AI Agents in a Real-time Shared Workspace Task

Shao Zhang , Xihuai Wang , Wenhao Zhang , Yongshan Chen , Landi Gao , Dakuo Wang , Weinan Zhang , Xinbing Wang
show 1 more author
Ying Wen
This is my paper

pith:5HFE2FAUopen to challenge →

classification cs.HC cs.AIcs.MA
keywords communicationagentagentscapabilitycollaborationhumanmindmtom
0
0 comments X
read the original abstract

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.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 4 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Theory of Mind in Action: The Instruction Inference Task in Dynamic Human-Agent Collaboration

    cs.CL 2025-06 conditional novelty 6.0

    Tomcat, an LLM agent using few-shot chain-of-thought or commonsense prompting, matches human performance on intent accuracy, action optimality, and planning optimality in a dynamic collaborative task.

  2. What Types of Human-AI Teams Exist?

    cs.HC 2026-07 unverdicted novelty 5.0

    Analysis of 53 human-AI team papers yields five distinct clusters (AI Assistant, Ad-hoc Dependency, Ad-hoc Forced Dependency, Paired Equanimity, Group Equanimity) based on psychological team characteristics.

  3. Interaction-Centered Intelligence: Toward an Interaction-Based Theory of Human-AI Co-Creation

    cs.AI 2026-05 unverdicted novelty 5.0

    Proposes Interaction-Centered Intelligence as a framework where intelligence emerges from interaction dynamics rather than internal agent computation.

  4. Medical Model Synthesis Architectures: A Case Study

    cs.AI 2026-05 unverdicted novelty 5.0

    MedMSA framework retrieves knowledge via language models then builds formal probabilistic models to produce uncertainty-weighted differential diagnoses from symptoms.