Search

huggingface.co › papers › 2608.04964

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

…Self-Verifiable Reinforcement Learning for Long-Horizon Video World Models Published on Aug 5 Submitted by Fury James on Aug 6 Tencent Authors: , , , Dazhao Du , , , , , , , , Abstract WorldCycle uses reversible action cycles to…

Aug 6, 2026

huggingface.co › papers › 2605.06200

Paper page - A^2TGPO: Agentic Turn-Group Policy Optimization with Adaptive Turn-level Clipping

…Agentic Turn-Group Policy Optimization with Adaptive Turn-level Clipping Published on May 7 Submitted by Dingwei Chen on May 8 Tencent Authors: Dingwei Chen , , , , , , , Abstract Reinforcement learning for agentic LLMs suffers…

May 8, 2026