NeoHorse-1: Towards Recursive Self-Improvement via Agentic Post-Training with Routing Harness Paper • 2609.08183 • Published 3 days ago • 386
RoboTok: An Internet-Scale Data Engine for Human Demonstration Retrieval and Dexterous Manipulation Learning Paper • 2609.03199 • Published 9 days ago • 116
Repo-To-Skill: Distilling GitHub Repositories Into AI4AI Skills Paper • 2609.02749 • Published 9 days ago • 540
HarnessDev: Can LLMs Create and Evolve Their Own Agent Harness? Paper • 2609.01437 • Published 10 days ago • 264
Scaling Large Reasoning Models beyond Human Supervision: A Path toward Superintelligence Paper • 2608.31075 • Published 11 days ago • 31
HarnessEval-W: Agentifying the Evaluation of Visual Worlds Paper • 2608.16859 • Published 25 days ago • 340
ABot-World-0: Infinite Interactive World Rollout on a Single Desktop GPU Paper • 2607.19191 • Published Jul 21 • 313
MetaView: Monocular Novel View Synthesis with Scale-Aware Implicit Geometry Priors Paper • 2607.12000 • Published Jul 13 • 40