Papers with fine-grained offline RL framework
Unearthing Gems from Stones: Policy Optimization with Negative Sample Augmentation for LLM Reasoning (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Recent advances in reasoning language models have witnessed a paradigm shift from short to long CoT pattern. |
| Approach: | They propose a behavior-constrained policy gradient with negative sample augmented (BCPG-NSA) negative steps are valuable components in long CoT models, authors argue . |
| Outcome: | The proposed framework outperforms baselines on math/coding reasoning benchmarks using the same training dataset. |