Thinking Ahead: Foresight Intelligence in MLLMs and World Models

Zhantao Gong1, Liaoyuan Fan2, Qing Guo1, Xun Xu3, Xulei Yang3, Shijie Li3
1Nankai University
2The University of Hong Kong
3Institute for Infocomm Research (I2R), A*STAR, Singapore
Paper arXiv Code Data

Abstract

In this work, we define Foresight Intelligence as the capability to anticipate and interpret future events—an ability essential for applications such as autonomous driving, yet largely overlooked by existing research. To bridge this gap, we introduce FSU-QA, a new Visual Question-Answering (VQA) dataset specifically designed to elicit and evaluate Foresight Intelligence. Using FSU-QA, we conduct the first comprehensive study of state-of-the-art Vision–Language Models (VLMs) under foresight-oriented tasks, revealing that current models still struggle to reason about future situations. Beyond serving as a benchmark, FSU-QA also enables the assessment of world models by measuring the semantic coherence of their generated predictions, quantified through performance gains when VLMs are augmented with such outputs. Our experiments further demonstrate that FSU-QA can effectively enhance foresight reasoning: even small VLMs fine-tuned on FSU-QA surpass much larger, advanced models by a substantial margin. Together, these findings position FSU-QA as a principled foundation for developing next-generation models capable of truly anticipating and understanding future events.

BibTeX

@misc{gong2025thinkingaheadforesightintelligence,
      title={Thinking Ahead: Foresight Intelligence in MLLMs and World Models},
      author={Zhantao Gong and Liaoyuan Fan and Qing Guo and Xun Xu and Xulei Yang and Shijie Li},
      year={2025},
      eprint={2511.18735},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2511.18735},
}