Tag
The paper introduces GapFT, a fine-tuning method that selects training examples based on a model's Pass@K–Pass@1 gap, showing on LogiQA 2.0 and ReClor that it raises single-sample accuracy dramatically while using far less data than uniform verified RFT.
This paper proposes using Evolution Strategies (ES) instead of Reinforcement Learning for post-training LLMs, showing that ES improves solution coverage (pass@k) and achieves better results on math benchmarks.