让AI学物理，先让它学会玩游戏
训练AI理解物理世界，现在的主流做法是喂更多视频、堆更多算力。这篇论文说这路子效率太低：视频只是画面，AI看完还是不知道东西会不会倒、能不能走过去。真正的解法藏在游戏引擎里——引擎里的场景是“可执行的”，碰撞、重力、能不能走通，引擎一算就知道，这就是AI训练最缺的“对错信号”。研究者提出一套新训练范式：让AI在游戏引擎里生成场景，引擎负责检查物理规则，人负责判断场景合不合理，两个信号合起来给AI当老师。它不是你明天能用上的东西，但它指了个方向：与其让AI看世界，不如让AI动手搭世界。
📄 原文摘要(英文)
A common strategy for scaling world models is to train on more crawled video with more compute. We argue that this strategy is inefficient: scaling world models also requires a recursive data engine that offers grounded reward signals. The success of code agents illustrates why this matters. As code is executable, compilers and runtimes can provide high-quality rewards for Reinforcement Learning (RL) post-training of LLMs. By contrast, spatial generation still relies largely on fuzzy proxies such as CLIP scores. These signals are fuzzy and biased, making them hard to support RL post-training. Compared with these, game development provides a missing reward environment for spatial world models. A scene encoded by a game engine is an executable world specification: the engine can efficiently check collision, physics, navigability and bounded playability, while the developer provides the global verification signal by judging whether the scene should be accepted. Game development also provides real-world long-horizon trajectory data for RL post-training. We therefore propose Reinforcement Learning with Human-Engine Verification (RLHEV), a post-training paradigm that combines dense engine signals with implicit human acceptance feedback from the development process.