Crimson AI NewsA CrimsonLingua Network service
EN ع
← Back to news
Research paper Hugging Face

β-OPSD: A Principled Generalization of On-Policy Self-Distillation for Reasoning Models

AI By Crimson AI Hugging Face Papers 1 August 2026 · 00:00 28 views
Share: X Telegram

Researchers introduce β-OPSD, a generalization of on-policy self-distillation that turns a fixed KL penalty into a tunable parameter, improving stability and performance on math reasoning benchmarks.

β-OPSD: A Principled Generalization of On-Policy Self-Distillation for Reasoning Models

Key points

On-policy self-distillation (OPSD) has shown promise for improving reasoning language models, but its practical application is often brittle and requires significant engineering effort. A new paper identifies a structural cause: vanilla OPSD is exactly the β=1 case of a broader policy-optimization family, where β weights the KL penalty that anchors the student to a reference policy.

By making β a controllable regularization parameter, the authors derive β-OPSD, whose optimal policy is a geometric interpolation between the reference policy and a privileged teacher. Rather than directly optimizing the costly and high-variance reinforcement learning objective, they convert its closed-form solution into an efficient token-level distillation target, mixing logits from the reference and teacher according to β.

This approach approximates expensive policy optimization with inexpensive distillation, while return-to-go credit assignment aligns token updates with sequence-level outcomes. Experiments on mathematical reasoning benchmarks with Qwen3 models (1.7B to 8B) show that β-OPSD consistently outperforms vanilla OPSD, improving both optimization stability and downstream reasoning performance.

The authors report a +5.74-point average gain at the 1.7B scale, highlighting the practical benefits of their method. The work provides a principled bridge between self-distillation and policy optimization, retaining the efficiency that makes OPSD practical.

Model ScaleAverage Gain (β-OPSD vs. vanilla OPSD)
1.7B+5.74 points
Source
Hugging Face · Hugging Face Papers
Related news
Research paper
Hugging Face 31 Aug 2026

Hugging Face Unveils StepGuard: Step-Level Guardrails for Safer AI Agents

StepGuard, a new step-level guard model from Hugging Face, audits agent actions before execution, reducing attack success rates by...

1
Research paper
Hugging Face 31 Aug 2026

Hugging Face Researchers Unveil ABot-Recon for Stable Long-Horizon 3D Reconstruction

ABot-Recon, a new streaming 3D reconstruction model from Hugging Face, achieves stable long-horizon performance using only local t...

1
Research paper
Hugging Face 31 Aug 2026

ContextPilot: Teaching Agents Proactive Context Management via Fine-Grained RL

Hugging Face researchers introduce ContextPilot, a framework that enhances long-horizon agent reasoning by expanding context-editi...

1