The Best of N Worlds: Aligning Reinforcement Learning with Best-of-N Sampling via max@k Optimisation Paper • 2510.23393 • Published Oct 27 • 20 • 1
Diff-XYZ: A Benchmark for Evaluating Diff Understanding Paper • 2510.12487 • Published Oct 14 • 8 • 2
Long Code Arena: a Set of Benchmarks for Long-Context Code Models Paper • 2406.11612 • Published Jun 17, 2024 • 25 • 3