StateM: Reaching 95.3% Raw Accuracy, or a \$15 Frontier Run, on Terminal-Bench 2.1 via Harness Scaling Paper • 2608.15089 • Published 4 days ago • 221
F2LLM Technical Report: Matching SOTA Embedding Performance with 6 Million Open-Source Data Paper • 2510.02294 • Published Oct 2, 2025 • 48