OPSD functions primarily as a compression stage after RLVR in mathematical reasoning, preserving accuracy on correct rollouts but reducing it on incorrect ones, supporting a SFT-then-RLVR-then-OPSD pipeline.
Mitigating overthinking in large reasoning models via difficulty-aware reinforcement learning.arXiv preprint arXiv:2601.21418
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3representative citing papers
CRISP achieves 57-59% token reduction on MATH-500 with 9-16 point accuracy gains on Qwen3 models via iterative self-distillation of concise reasoning behavior.
AdaGRPO gates GRPO reinforcement learning with supervised NLL using per-sample binary clips based on policy difficulty and reward discriminability, raising HR@10 from 11.01% to 12.18% while keeping hallucination below 0.22% on large-scale e-commerce data and showing A/B gains.
citing papers explorer
-
OPSD Compresses What RLVR Teaches: A Post-RL Compaction Stage for Reasoning Models
OPSD functions primarily as a compression stage after RLVR in mathematical reasoning, preserving accuracy on correct rollouts but reducing it on incorrect ones, supporting a SFT-then-RLVR-then-OPSD pipeline.
-
CRISP: Compressed Reasoning via Iterative Self-Policy Distillation
CRISP achieves 57-59% token reduction on MATH-500 with 9-16 point accuracy gains on Qwen3 models via iterative self-distillation of concise reasoning behavior.
-
Adaptive Loss Balancing for Noise-Robust GRPO in Generative Recommendation
AdaGRPO gates GRPO reinforcement learning with supervised NLL using per-sample binary clips based on policy difficulty and reward discriminability, raising HR@10 from 11.01% to 12.18% while keeping hallucination below 0.22% on large-scale e-commerce data and showing A/B gains.