Dream-RSI: Recursive Self-Improvement through Evolving Worlds Paper • 2609.14858 • Published 4 days ago • 289
NeoHorse-1: Towards Recursive Self-Improvement via Agentic Post-Training with Routing Harness Paper • 2609.08183 • Published 10 days ago • 420
WarpSAC: Towards the Pinnacle of Scalable Off-policy RL by Rethinking Exploration and Exploitation Paper • 2608.24479 • Published 24 days ago • 144
Macaron-V1: Towards Open Continual Learning with Self-Improvement and Mixture-of-LoRA Paper • 2608.09819 • Published Aug 10 • 345