# WorldCycle：面向长程视频世界模型的自验证强化学习

- 来源：HuggingFace Daily Papers（社区热门论文）
- 发布时间：2026-08-05 08:00
- AIHOT 分数：45
- AIHOT 链接：https://aihot.virxact.com/items/cmsgxbipf02rbroxz6n84cvd6
- 原文链接：https://arxiv.org/abs/2608.04964

## AI 摘要

WorldCycle 提出一种自验证强化学习框架，通过可逆动作循环构造闭环动作序列，无需人工标注即可监督长程正确性。该方法优化空间闭合与时间一致性两类奖励，使模型将动作视为一致的状态算子。WorldCycle 将状态回归漂移降低最多 44%，复合动作准确率较基础模型提升近 4 倍，并发布诊断基准 CycleBench。

## 正文

Interactive video world models are essential for long-horizon planning and exploration, yet they suffer from compounding errors. Post-training methods such as reinforcement learning (RL) can improve these models, but they hit a verification bottleneck: for arbitrary action sequences, no ground-truth future state exists to measure long-term drift. Our key insight is that reversible action cycles make this verification possible: a sequence composed with its inverse must analytically return to the initial state, yielding annotation-free supervision on long-horizon correctness. Building on this, we introduce WorldCycle, a self-verifiable RL framework that constructs closed action cycles and their repeated executions from ordinary action sequences, and optimizes two complementary rewards: a spatial closure reward enforcing symmetry between mirrored forward and reverse segments, and a temporal consistency reward aligning states across repeated cycle executions. These rewards force the model to learn actions as consistent state operators rather than memorized temporal patterns, and extend naturally to out-of-distribution composite action cycles that the base model handles poorly. We further release CycleBench, a diagnostic benchmark for state-returning ability under complex action structures. WorldCycle reduces state returning drift by up to 44% and lifts composite-action accuracy nearly 4x over the base model, providing a vital foundation for physically grounded world models.