RL for LLMs has a Matthew Effect where hard problems get ignored—this post proposes Never Give Up to fix it

Learning to solve hard problems in RL for LLMs by never giving up

Michael Noukhovitch's blog walks through his new paper on the Matthew Effect in RL post-training for LLMs: as training progresses, the model samples easy problems more and hard problems less, because early successes on easy tasks dominate the reward signal. His proposed fix, Never Give Up (NGU), forces a minimum sampling ratio for hard problems so they don't get squeezed out. On Olmo 3.1 7B math training, NGU lifts AIME 2025 pass@1 from 26.7% to 33.3%; on code, LiveCodeBench pass@1 goes from 23.4% to 26.1%. The post also covers async RL staleness tricks and frames the Matthew Effect as a form of primacy bias. The body doesn't disclose NGU's specific hyperparameters or extra compute cost, so I'd discount the gains until those details surface.

Why it matters: Michael Noukhovitch turns his paper on the Matthew Effect in RL post-training into a highly readable blog post: models increasingly favor easy problems during training, and hard-problem sampling rates keep dropping. His proposed NGU method enforces a minimum sampling ratio for...