paper-with-me

홈 › Papers

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

2026-08-05 · Bohai Gu, Yueyang Yuan, Taiyi Wu, Dazhao Du, Jian Liu, Xiaoyi Pang, Jie Zhang, Xiaocheng Lu, Haobin Zhong, Xiaotong Zhao, Alan Zhao, Song Guo hf

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.

📄 PDF Abstract BibTeX arXiv:2608.04964

Code (3)

Aaron617/agent-arXiv-daily ★ 10
BaiShuanghao/my_arXiv_daily ★ 208
Tavish9/awesome-daily-AI-arxiv ★ 113

Tasks

Reinforcement Learning

Similar Papers 제목 키워드 기반

DeepSearch-World: Self-Distillation for Deep Search Agents in a Verifiable Environment

2026-07-08 · Xinyu Geng, Xuanhua He, Sixiang Chen, Yanjing Xiao 외 arxiv

Training tool-use agents to improve from their own experience remains challenging, as supervised fine-tuning relies on fixed teacher-distilled trajectories, while sparse-reward reinforcement learning provides weak superv…

Reinforcement Learning

Audited Skill-Graph Self-Improvement for Agentic LLMs via Verifiable Rewards, Experience Synthesis, and Continual Memory

2025-12-28 · Ken Huang, Jerry Huang arxiv

Reinforcement learning is increasingly used to transform large language models into agentic systems that act over long horizons, invoke tools, and manage memory under partial observability. While recent work has demonstr…

Reinforcement Learning

Rewarding Beliefs, Not Actions: Consistency-Guided Credit Assignment for Long-Horizon Agents

2026-05-19 · Wenjie Tang, Minne Li, Sijie Huang, Liquan Xiao 외 arxiv

Reinforcement learning from verifiable rewards (RLVR) is a promising paradigm for improving large language model (LLM) agents on long-horizon interactive tasks. However, in partially observable environments, incomplete o…

Reinforcement Learning

Policy-Conditioned Counterfactual Credit for Verifiable Reinforcement Learning of Long-Horizon Language Agents

2026-06-03 · Renwei Meng arxiv

Reinforcement learning with verifiable rewards improves reasoning and tool use, yet long-horizon language agents still learn unsupported evidence chains, belief drift, and shortcut actions that satisfy terminal checks. E…

Reinforcement Learning

Contrastive Reinforced Policy Optimization via Privileged Self-Distillation

2026-07-30 · Xingjian Wu, Junlin Liu, Xingchen Liu, Xuhang Zhu 외 arxiv

Recent advances in post-training Large Language Models (LLMs) increasingly rely on Reinforcement Learning with Verifiable Rewards (RLVR) or On-Policy Self-Distillation (OPSD). While OPSD provides dense, logit-level super…

Reinforcement LearningContrastive Learning