Lululzz/Causal_Planner

Token Predictors Are Not Planners: Building Physically Grounded Causal Reasoners

Zheng Lu^1,2,, Mingqi Gao^1,, Qinlei Xie^1,*, Wanqi Zhong¹, Hanwen Cui¹, Heng Cao¹, Zirui Song³, Yifan Yang², Chong Luo², Bei Liu^2,†, Yiming Li^1,†

¹Tsinghua University    ²Microsoft Research Asia    ³MBZUAI

^*Equal contribution    ^†Corresponding authors

Model Overview

This repository hosts the Causal Planner model checkpoint released with Token Predictors Are Not Planners: Building Physically Grounded Causal Reasoners. The model is designed for physically grounded embodied planning, emphasizing causal preconditions, action-induced state transitions, long-horizon composition, and recovery under failures.

Resources

• Model: https://huggingface.co/Lululzz/Causal_Planner
• Dataset: https://huggingface.co/datasets/anonymous-causal-plan/Causal_Plan/tree/main/CausalPlan-1M-QA
• Benchmark: https://huggingface.co/datasets/anonymous-causal-plan/Causal_Plan/tree/main/Causal-Plan-Bench

License

This model card is released under the Apache-2.0 license metadata shown above. Dataset and benchmark usage should follow the corresponding Hugging Face repository terms.