DPMT: Dual Process Multi-scale Theory of Mind Framework for Real-time Human-AI Collaboration

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Li, Xiyun, Ding, Yining, Jiang, Yuhua, Zhao, Yunlong, Xie, Runpeng, Xu, Shuang, Ni, Yuanhua, Yang, Yiqin, Xu, Bo
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915398177259520
author Li, Xiyun
Ding, Yining
Jiang, Yuhua
Zhao, Yunlong
Xie, Runpeng
Xu, Shuang
Ni, Yuanhua
Yang, Yiqin
Xu, Bo
author_facet Li, Xiyun
Ding, Yining
Jiang, Yuhua
Zhao, Yunlong
Xie, Runpeng
Xu, Shuang
Ni, Yuanhua
Yang, Yiqin
Xu, Bo
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2507_14088
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle DPMT: Dual Process Multi-scale Theory of Mind Framework for Real-time Human-AI Collaboration
Li, Xiyun
Ding, Yining
Jiang, Yuhua
Zhao, Yunlong
Xie, Runpeng
Xu, Shuang
Ni, Yuanhua
Yang, Yiqin
Xu, Bo
Machine Learning
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.
title DPMT: Dual Process Multi-scale Theory of Mind Framework for Real-time Human-AI Collaboration
topic Machine Learning
url https://arxiv.org/abs/2507.14088