The Best of N Worlds: Aligning Reinforcement Learning with Best-of-N Sampling via max@k Optimisation Paper • 2510.23393 • Published Oct 27 • 20
The Complexity Trap: Simple Observation Masking Is as Efficient as LLM Summarization for Agent Context Management Paper • 2508.21433 • Published Aug 29 • 7
JetBrains-Research/OpenCoder-1.5B-Text-Chunks-Py-Irrelevant Text Generation • 2B • Updated Oct 17 • 17
JetBrains-Research/OpenCoder-1.5B-Declarations-Py-Irrelevant Text Generation • 2B • Updated Oct 17 • 21
JetBrains-Research/OpenCoder-1.5B-Declarations-Py-Reversed Text Generation • 2B • Updated Oct 17 • 14