Extrapolative Weight Averaging Reveals Correctness-Efficiency Frontiers in Code RL 事件

Extrapolative Weight Averaging Reveals Correctness-Efficiency Frontiers in Code RL arXiv:2605.28751v1 Announce Type: cross Abstract: Linear interpolation between fine-tuned checkpoints has been shown to trace the Pareto front between competing objectives, but whether extrapolative weight averaging can extend such frontiers to new checkpoints useful at inference time, without additional RL training, remains unclear. We study this question in RL for competitive programming, where hidden unit test