Cliff is a reward‑shaping method for reinforcement learning with verifiable rewards that identifies the first mistake in a language model’s reasoning process using an off‑the‑shelf teacher. It splits each rollout into a correct prefix and an incorrect suffix, assigning positive token‑level advantages to the prefix and negative feedback to the suffix. Across 12 scenarios, Cliff improves reasoning performance, outperforming on‑policy distillation by 15% and standard GRPO by 7%, even with modest teachers.
SIPO (Self‑Instructing Policy Optimization) unifies reinforcement learning with on‑policy self‑distillation by using a contrastive self‑teacher to generate token‑level credit signals. The method samples multiple rollouts per prompt, pairs each with a reference answer and its mistakes, and uses the difference in teacher log‑probabilities to provide dense feedback while still respecting the overall task reward. Experiments on reasoning and code‑generation benchmarks show that SIPO outperforms both RLVR and OPSD baselines without requiring an external teacher or extra generation steps.
By Zhenrui Yue, Huimin Zeng, Yueqi Wang, Yaokun Liu, Fengran Mo, Jinghan Zhang, Mung Yao Jia, Gyuseok Lee, Yang Zhang, Na Wei, Dong Wang
The paper investigates how to combine on‑policy distillation (OPD) and reinforcement learning with verifiable rewards (RLVR) for post‑training reasoning in large language models. It finds that a simple two‑stage approach—first applying OPD, then switching to RL—outperforms single‑signal methods and other joint baselines on logic and math reasoning benchmarks. The authors explain this advantage by showing that OPD broadens the model’s coverage of teacher‑supported solutions while RL sharpens performance within that support, and they provide practical guidance on when to switch based on OPD validation scores.
The paper investigates how on-policy distillation (OPD) and reinforcement learning with verifiable rewards (RLVR) can be combined for post‑training reasoning in large language models. It shows that a two‑stage approach—first applying OPD, then RL—outperforms single‑signal methods and other joint baselines on logic and math reasoning benchmarks. The authors explain this advantage through pass@k analysis, learning dynamics, and parameter updates, concluding that OPD expands solution coverage while RL sharpens performance within that support, and that the OPD validation score is the key trigger for switching to RL.
By Boyan Li, Bingsen Chen, Chenghao Yang, Ping Nie, Chen Zhao, Xi Ye
arXiv:2610. 22887v1 Announce Type: cross Abstract: Long rollout windows make reinforcement learning with verifiable rewards (RLVR) expensive, yet simply shortening them can remove the correctness signal: when every single-problem rollout truncates before an answer, group-relative accuracy advantages vanish.
By Bangji Yang, Hongbo Ma, Ruihan Guo, Jiajun Fan, Xi Zhu, Ge Liu
Post-training of reasoning language models is commonly driven by supervised distillation and reinforcement learning with verifiable rewards. Distillation often relies on chain-of-thought annotations that are expensive to obtain and may themselves be noisy, incomplete, or partially incorrect; even when the final solution is correct, an imperfect rationale can interfere with learning.