Planning Takes More Than Token Prediction: Causal Plan for Benchmarking and Building Physically Grounded Embodied Reasoners
This work introduces Causal-Plan-Bench, a high-fidelity diagnostic suite spanning four causal dimensions, curated via multi-stage verification, and initiate the first effort to turn agents from superficial token predictors into physically grounded causal reasoners, bridging language modeling and world modeling.
Zi-Rong Song, Zheng Lu, Ming-Qi Gao et al.
· 3 citations