Vision-Language-Action (VLA) models convert high-level language instructions into concrete, executable actions, a task that is especially challenging in open-world environments. We present Visual Foresight Planning (ForeAct), a general and efficient planner that guides a VLA step-bystep using imagined future observations and subtask descriptions. With an imagined future observation, the VLA can focus on visuo-motor inference rather than high-level semantic reasoning, leading to improved accuracy and generalization. Our planner comprises a highly efficient foresight image generation module that predicts a high-quality 640×480 future observation from the current visual input and language instruction within only 0.33s on an H100 GPU, together with a vision-language model that reasons over the task and produces subtask descriptions for both the generator and the VLA. Importantly, state-of-the-art VLAs can integrate our planner seamlessly by simply augmenting their visual inputs, without any architectural modification. The foresight generator is pretrained on over 1 million multi-task, cross-embodiment episodes, enabling it to learn robust embodied dynamics. We evaluate our framework on a benchmark that consists of 11 diverse, multi-step realworld tasks. It achieves an average success rate of 87.4%, demonstrating a +40.9% absolute improvement over the π0 baseline (46.5%) and a +30.3% absolute improvement over π0 augmented with textual subtask guidance (57.1%).
@article{zhang2026foreact, title={Foreact: Steering your vla with efficient visual foresight planning}, author={Zhang, Zhuoyang and Yang, Shang and Hu, Qinghao and Huang, Luke J and Hou, James and Sun, Yufei and Lu, Yao and Han, Song}, journal={arXiv preprint arXiv:2602.12322}, year={2026}}
