NeoHorse-1: Towards Recursive Self-Improvement via Agentic Post-Training with Routing Harness Paper • 2609.08183 • Published 8 days ago • 414
Repo-To-Skill: Distilling GitHub Repositories Into AI4AI Skills Paper • 2609.02749 • Published 14 days ago • 550
HarnessDev: Can LLMs Create and Evolve Their Own Agent Harness? Paper • 2609.01437 • Published 15 days ago • 268
electricsheepafrica/africa-ghana-national-accident-statistics-by-age-group-819d734e Viewer • Updated Aug 11 • 400 • 13 • 1
Safety Testing LLM Agents at Scale: From Risk Discovery to Evidence-Grounded Verification Paper • 2607.01793 • Published Jul 4 • 8