SOURCE-LINKED INTELLIGENCE

Learning to Solve Hard Problems in RL for LLMs by Never Giving Up

arXiv · AI, language, vision and robotics · article · Sep 11, 2026 · UTC

We demonstrate that training LLMs with RL does not improve performance equally across a dataset. RL shows large improvements on easy problems that an LLM is already good at solving, but small improvements on hard problems. We call this the Matthew Effect in RL for LLMs, after the phenomenon of cumulative advantage from economics and network science summarized as "the rich get richer". The naive explanation is that hard problems require more compute to find a solution. We argue that modern RL methods are exacerbating the issue by wasting too much compute on easy problems and instead should dyna

Read original source ↗ Open in workspace

recordType

paper

region

Global