DPMT: Dual Process Multi-scale Theory of Mind Framework for Real-time Human-AI Collaboration
This work addresses the problem of AI agents adapting to diverse human behaviors in dynamic scenarios for improved collaboration, though it appears incremental as it builds on existing cognitive science theories.
The paper tackles the challenge of real-time human-AI collaboration by proposing a dual process multi-scale theory of mind (DPMT) framework to model complex human mental characteristics, such as domain intentions, without direct communication, and demonstrates that DPMT significantly enhances collaboration performance.
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.