CodeMidas: Scaling Agentic Coding RL Environments from Code Itself Paper • 2609.22068 • Published 7 days ago • 131
NeoHorse-1 Collection NeoHorse-1: Towards Recursive Self-Improvement via Agentic Post-Training with Routing Harness • 3 items • Updated 16 days ago • 8
NeoHorse-1: Towards Recursive Self-Improvement via Agentic Post-Training with Routing Harness Paper • 2609.08183 • Published 17 days ago • 174
On the Design of Qwen3.8-Next Architecture: Evaluation, Efficiency, and Training Stability Paper • 2608.30320 • Published 25 days ago • 63
deepseek-ai/DeepSeek-V4-Flash-Vision-Exp Image-Text-to-Text • 305B • Updated 24 days ago • 889k • • 927
Agentic Artifact Creation: Systems, Evaluation, Principles, and Opportunities Paper • 2608.28122 • Published 28 days ago • 66