EliteReplay: Preserving Diverse Solutions in RL Post-Training via Quality-Diversity Search
arXiv:2610.22290v1 Announce Type: new Abstract: Reinforcement learning has become a common post-training technique to improve the accuracy of LLMs on verifiable tasks. However, such training can narrow the set of solutions the model can produce. Several approaches have attempted to address this behavior-sharpening effect, but they often optimize metrics that do not reflect the diversity of correct solutions. Ideally, we want a model that can produce multiple good solutions, not only a single re…