Dream-RSI: Recursive Self-Improvement through Evolving Worlds Paper • 2609.14858 • Published 16 days ago • 250
gradients-io-tournaments/tournament-exp-s1-6d8b2af6-9715-4a60-bc19-b7e8023b57a2-5Exp6849a93f7e12faf6 2B • Updated 17 days ago • 19 • 1
NeoHorse-1: Towards Recursive Self-Improvement via Agentic Post-Training with Routing Harness Paper • 2609.08183 • Published 22 days ago • 327
HarnessEval-W: Agentifying the Evaluation of Visual Worlds Paper • 2608.16859 • Published Aug 17 • 122
Macaron-V1: Towards Open Continual Learning with Self-Improvement and Mixture-of-LoRA Paper • 2608.09819 • Published Aug 10 • 178