Proximal KL Beats GRPO by 2.58% When AI Training Data Goes Stale

A new RLVR training method called Proximal KL swaps PPO-style clipping for bounded future-KL credit, beating GRPO by up to 2.58% on math benchmarks.

Source

AlphaSignal

Published

Oct 13, 2026, 5:09 PM

Author

AlphaSignal Newsroom

Read

1 min read

A new RLVR training method called Proximal KL swaps PPO-style clipping for bounded future-KL credit, beating GRPO by up to 2.58% on math benchmarks.

Reporting is indexed from AlphaSignal. Rights remain with the original publisher and cited sources.

Next reads

$MIT Finds a Simple Word Prefix Boosts AI Math Scores by 36 Points$