Real-time human-artificial intelligence (AI) collaboration is crucial yet challenging, especially when AI agents must adapt to diverse and unseen human behaviors in dynamic scenarios. Existing large language model (LLM) agents often fail to accurately model the complex human mental characteristics such as domain intentions, especially in the absence of direct communication. To address this limitation, we propose a novel dual process multi-scale theory of mind (DPMT) framework, drawing inspiration from cognitive science dual process theory. Our DPMT framework incorporates a multi-scale theory of mind (ToM) module to facilitate robust human partner modeling through mental characteristic reasoning. Experimental results demonstrate that DPMT significantly enhances human-AI collaboration, and ablation studies further validate the contributions of our multi-scale ToM in the slow system.
@article{arxiv.2507.14088,
title = {DPMT: Dual Process Multi-scale Theory of Mind Framework for Real-time Human-AI Collaboration},
author = {Xiyun Li and Yining Ding and Yuhua Jiang and Yunlong Zhao and Runpeng Xie and Shuang Xu and Yuanhua Ni and Yiqin Yang and Bo Xu},
journal= {arXiv preprint arXiv:2507.14088},
year = {2025}
}