WorldCycle: Self-Verifiable Reinforcement Learning for Long-Horizon Video World Models

arXiv:2608.04964 · cs.AI, cs.LG · Submitted 2026-08-05 · Read on arXiv

Bohai Gu, Yueyang Yuan, Taiyi Wu, Dazhao Du, Jian Liu, Xiaoyi Pang, Jie Zhang, Xiaocheng Lu, Haobin Zhong, Xiaotong Zhao, Alan Zhao, Song Guo

cs.AI, cs.LG

Submitted: 2026-08-05

Comments: https://nevsnev.github.io/Worldcycle/

Project page: https://nevsnev.github.io/Worldcycle

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• World Model — 47× in this paper · explained in 7 episodes
• Consistency — 40× in this paper · explained in 3 episodes
• Benchmark — 17× in this paper · explained in 2 episodes
• Reinforcement Learning — 13× in this paper · explained in 4 episodes
• Accuracy — 11× in this paper · explained in 1 episode
• Temporal Consistency — 10× in this paper · explained in 3 episodes
• Verification — 10× in this paper · explained in 2 episodes
• Diffusion Model — 6× in this paper · explained in 10 episodes
• Fidelity — 6× in this paper · explained in 2 episodes
• Ablation — 5× in this paper · explained in 1 episode
• Diffusion Models — 5× in this paper · explained in 9 episodes
• GRPO — 4× in this paper · explained in 6 episodes
• Autoregressive Rollout — 3× in this paper · explained in 3 episodes
• Generalization — 3× in this paper · explained in 13 episodes
• Endpoint State Closure — 2× in this paper
• Foundation Model — 2× in this paper · explained in 3 episodes
• Latent Dynamics — 2× in this paper · explained in 2 episodes
• RLVR — 2× in this paper · explained in 2 episodes
• Regularization — 2× in this paper · explained in 3 episodes
• Reinforcement Learning (RL) — 2× in this paper · explained in 25 episodes
• Repeated-Cycle Stability — 2× in this paper
• Reverse-Path Symmetry — 2× in this paper
• Sparsity — 2× in this paper · explained in 4 episodes
• Transformer — 2× in this paper · explained in 2 episodes
• Ablation Study — 1× in this paper · explained in 3 episodes
• Adam — 1× in this paper · explained in 2 episodes
• Benchmarking — 1× in this paper · explained in 4 episodes
• Coherence — 1× in this paper · explained in 2 episodes
• Conservation Laws — 1× in this paper · explained in 3 episodes
• Credit assignment — 1× in this paper · explained in 3 episodes
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• Flow Matching — 1× in this paper · explained in 15 episodes
• Flow Matching Model — 1× in this paper · explained in 3 episodes
• Generative Model — 1× in this paper · explained in 2 episodes
• Generative Models — 1× in this paper · explained in 3 episodes
• Generator — 1× in this paper · explained in 2 episodes
• Grounding — 1× in this paper · explained in 3 episodes
• Latent Representation — 1× in this paper · explained in 2 episodes
• Latent Representations — 1× in this paper · explained in 3 episodes
• Reward Function — 1× in this paper · explained in 4 episodes
• Reward Hacking — 1× in this paper · explained in 11 episodes
• Training Objective — 1× in this paper · explained in 2 episodes
• Transformers — 1× in this paper · explained in 2 episodes
• Verifier — 1× in this paper · explained in 2 episodes

Sources

• VRAG: Learning World Models for Interactive Video Generation
• Vista: A Generalizable Driving World Model with High Fidelity and Versatile Controllability
• Infinite Worlds with Versatile Interactions
• DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
• World Models
• GAIA-1: A Generative World Model for Autonomous Driving
• LIVE: Long-horizon Interactive Video World Modeling
• HY-World 2.0: A Multi-Modal World Model for Reconstructing, Generating, and Simulating 3D Worlds
• Flow-GRPO: Training Flow Matching Models via Online RL
• HPSv3: Towards Wide-Spectrum Human Preference Score
• Aligning Text-to-Image Diffusion Models with Reward Backpropagation
• DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
• Cycle-World: Mitigating Error Accumulation in Long-term Video World Models via Reverse-Prediction Cycle Consistency
• WorldPlay: Towards Long-Term Geometric Consistency for Real-Time Interactive World Modeling
• Diffusion Models Are Real-Time Game Engines
• World Models as Group Actions
• Video World Models with Long-term Spatial Memory
• Pandora: Towards General World Model with Natural Language Actions and Video States
• DanceGRPO: Unleashing GRPO on Visual Generation
• Reinforcement Learning with Inverse Rewards for World Model Post-training

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• Agents' Last Exam
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems