A dual-process LLM agent with a three-stage theory-of-mind module outperforms baselines in real-time Overcooked human-AI collaboration.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
DPMT: Dual Process Multi-scale Theory of Mind Framework for Real-time Human-AI Collaboration
A dual-process LLM agent with a three-stage theory-of-mind module outperforms baselines in real-time Overcooked human-AI collaboration.