Reasoning Cache: Continual Improvement Over Long Horizons via Short-Horizon RL Paper • 2602.03773 • Published 25 days ago • 11
Intelligent-Internet/swebench-pro-claude-sonnet-4.5-ii-agent-trajectories Viewer • Updated Nov 7, 2025 • 726 • 16 • 2
SamsungSDS-Research/SGuard-JailbreakFilter-2B-v1 Text Generation • 3B • Updated Dec 15, 2025 • 329 • 15
NemoGuard Collection Essential datasets and models for content safety, topic-following, and security guardrails • 13 items • Updated 5 days ago • 20