SPIRAL: A Closed-Loop Framework for Self-Improving Action World Models via Reflective Planning Agents
Yu Yang, Yue Liao, Jianbiao Mei, Baisen Wang, Xuemeng Yang, Licheng Wen, Jiangning Zhang, Xiangtai Li, Hanlin Chen, Botian Shi, Yong Liu, Shuicheng Yan, Gim Hee Lee
Unverified — Be the first to reproduce this paper.
ReproduceAbstract
We introduce SPIRAL, a self-improving planning and iterative reflective action world modeling closed-loop framework that enables controllable long-horizon video generation conditioned on high-level semantic actions. Existing one-shot video generation models operate in open-loop, often resulting in incomplete action execution, weak semantic grounding, and temporal drift. SPIRAL formulates ActWM as a closed-loop think-act-reflect process, where generation proceeds step by step under explicit planning and feedback. A PlanAgent decomposes abstract actions into object-centric sub-actions, while a CriticAgent evaluates intermediate results and guides iterative refinement with long-horizon memory. This closed-loop design naturally supports RL evolving optimization, improving semantic alignment and temporal consistency over extended horizons. We further introduce the ActWM-Dataset and ActWM-Bench for training and evaluation. Experiments across multiple TI2V backbones demonstrate consistent gains on ActWM-Bench and mainstream video generation benchmarks, validating SPIRAL's effectiveness.