ASI-Bench: At the Dawn of Artificial Superintelligence Paper β’ 2608.17271 β’ Published Aug 18 β’ 68
CodeNib: A Multi-View Data System for Serving Repository Context to Coding Agents Paper β’ 2607.25431 β’ Published Jul 28 β’ 110
The Verification Horizon: No Silver Bullet for Coding Agent Rewards Paper β’ 2606.26300 β’ Published Jun 24 β’ 54
Scaling Laws for Code: Every Programming Language Matters Paper β’ 2512.13472 β’ Published Dec 15, 2025 β’ 18
EvoClaw: Evaluating AI Agents on Continuous Software Evolution Paper β’ 2603.13428 β’ Published Mar 13 β’ 22