AI RESEARCH

A Task-Centric Theory for Iterative Self-Improvement with Easy-to-Hard Curricula

arXiv CS.LG

ArXi:2602.10014v2 Announce Type: replace Iterative self-improvement fine-tunes an autoregressive large language model (LLM) on reward-verified outputs generated by the LLM itself. In contrast to the empirical success of self-improvement, the theoretical foundation of this generative, iterative procedure in a practical, finite-sample setting remains limited. We make progress toward this goal by modeling each round of self-improvement as maximum-likelihood fine-tuning on a reward-filtered distribution and deriving finite-sample guarantees for the expected reward.