arXiv AI
Mitigating Distribution Sharpening in Math RLVR via Distribution-Aligned Hint Synthesis and Backward Hint Annealing
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv Computation and Language
Oct 9
Residual Advantage: Student-Relative Teacher Guidance for RL with Verifiable Rewards
The paper introduces Residual Advantage (RA), a new guidance method for reinforcement learning with verifiable rewards (RLVR) that treats the teacher–student probability residual as a bounded one‑step reward, subtracts the student’s state value to form an advantage, and centers it within each response. RA preserves the verifier’s mean label while redistributing credit among response steps, and its extension CoRA updates the teacher model using verifier advantages to adapt guidance to the student’s attempts. Experiments with Qwen3 models show that RA combined with GRPO or REINFORCE++ consistently outperforms teacher‑only on‑policy distillation across three mathematical benchmarks, improving macro Avg@8 and Pass@8 scores, with CoRA providing additional gains.
arXiv Machine Learning
Jul 30
Early Verdicts, Better Budgets: Sequential Adaptive Rollout Allocation for Compute-Efficient RLVR
arXiv:2607. 26253v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) is bottlenecked by rollout generation, yet many sampled prompts produce saturated groups (all responses correct or all incorrect) whose zero reward variance yields no policy-gradient signal.
arXiv AI
Oct 15
Beyond GRPO and On-Policy Distillation: An Empirical Sparse-to-Dense Reward Principle for Language-Model Post-Training
The paper proposes a reward‑density principle for language‑model post‑training: sparse sequence‑level rewards are best for exploring and discovering new behaviors in a strong teacher, while dense token‑level teacher supervision is optimal for compressing that behavior into a smaller deployment model. The authors validate this rule with a four‑stage workflow—teacher RL, forward‑KL warmup, on‑policy distillation, and optional post‑bridge student RL—showing that an RL‑improved 8B teacher distilled through a dense bridge outperforms direct GRPO on a 1.7B student across math and code benchmarks. Ablation studies confirm each stage’s contribution, and the approach generalizes to Llama and Qwen models, offering a practical guideline for allocating scarce labeled data.
arXiv Computation and Language
Sep 3
Zone of Proximal Policy Optimization: Teacher in Prompts, Not Gradients
The paper introduces Zone of Proximal Policy Optimization (ZPPO), a method that keeps a teacher model inside prompts rather than in the policy gradient to improve knowledge distillation for small students. ZPPO creates two types of reformulated prompts—Binary Candidate-included Questions (BCQ) and Negative Candidate-included Questions (NCQ)—to expose students to correct and incorrect responses, and uses a replay buffer to focus training on hard questions until the student’s accuracy improves. Experiments on the Qwen3.5 family with a 27B teacher across 31 benchmarks show that ZPPO outperforms both off‑policy and on‑policy distillation methods, especially at the smallest student scales.
arXiv AI
Jul 24
When RLVR Shrinks the Reasoning Boundary: Diagnosing Pass@k Inversion
arXiv:2607. 20543v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards (RLVR) can improve one-sample accuracy while making a model worse under repeated sampling.
arXiv AI
Aug 11
Mismatch Matters: On-Policy Distillation Beyond Token Agreement
arXiv:2608. 09836v1 Announce Type: new Abstract: On-policy distillation (OPD) has emerged as a core component of modern LLM post-training pipelines, yet we reveal a failure mode: degenerate agreement, where students exploit repetitive loops to achieve near-perfect token agreement with the teacher despite globally flawed responses.