Cover Image

Scaling Reasoning Efficiently via Relaxed On-Policy Distillation

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Ko, Jongwoo, Abdali, Sara, Kim, Young Jin, Chen, Tianyi, Cameron, Pashmina
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

DistiLLM: Towards Streamlined Distillation for Large Language Models
by: Ko, Jongwoo, et al.
Published: (2024)

DistiLLM-2: A Contrastive Approach Boosts the Distillation of LLMs
by: Ko, Jongwoo, et al.
Published: (2025)

From Belief Entrenchment to Robust Reasoning in LLM Agents
by: Oh, Jihwan, et al.
Published: (2025)

Thinking-Free Policy Initialization Makes Distilled Reasoning Models More Effective and Efficient Reasoners
by: Xu, Xin, et al.
Published: (2025)

Self-Distilled Reasoner: On-Policy Self-Distillation for Large Language Models
by: Zhao, Siyan, et al.
Published: (2026)

StableQAT: Stable Quantization-Aware Training at Ultra-Low Bitwidths
by: Chen, Tianyi, et al.
Published: (2026)

WINA: Weight Informed Neuron Activation for Accelerating Large Language Model Inference
by: Chen, Sihan, et al.
Published: (2025)

Efficient Data Selection at Scale via Influence Distillation
by: Nikdan, Mahdi, et al.
Published: (2025)

Decoding the AI Pen: Techniques and Challenges in Detecting AI-Generated Text
by: Abdali, Sara, et al.
Published: (2024)

SlimMoE: Structured Compression of Large MoE Models via Expert Slimming and Distillation
by: Li, Zichong, et al.
Published: (2025)

Near-Policy: Accelerating On-Policy Distillation via Asynchronous Generation and Selective Packing
by: Rang, Miao, et al.
Published: (2026)

Reasoning-preserved Efficient Distillation of Large Language Models via Activation-aware Initialization
by: He, Junlin, et al.
Published: (2026)

Efficiently Scaling LLM Reasoning with Certaindex
by: Fu, Yichao, et al.
Published: (2024)

Scaling Policy Compliance Assessment in Language Models with Policy Reasoning Traces
by: Imperial, Joseph Marvin, et al.
Published: (2025)

ROSD: Reflective On-Policy Self-Distillation for Language Model Reasoning across Domains
by: Zhao, Ziqi, et al.
Published: (2026)

Stepwise Guided Policy Optimization: Coloring your Incorrect Reasoning in GRPO
by: Chen, Peter, et al.
Published: (2025)

Decoder-Hybrid-Decoder Architecture for Efficient Reasoning with Long Generation
by: Ren, Liliang, et al.
Published: (2025)

Why Does Self-Distillation (Sometimes) Degrade the Reasoning Capability of LLMs?
by: Kim, Jeonghye, et al.
Published: (2026)

Efficient Mathematical Reasoning Models via Dynamic Pruning and Knowledge Distillation
by: Yu, Fengming, et al.
Published: (2025)

Critique-Guided Distillation for Robust Reasoning via Refinement
by: Kapusuzoglu, Berkcan, et al.
Published: (2025)

Towards Trustworthy Multimodal Moderation via Policy-Aligned Reasoning and Hierarchical Labeling
by: Li, Anqi, et al.
Published: (2025)

Trust Region On-Policy Distillation
by: Xing, Xingrun, et al.
Published: (2026)

OmniOPD: Logit-Free On-Policy Distillation via Speculative Verification
by: Zhou, Yuhang, et al.
Published: (2026)

Tokenisation via Convex Relaxations
by: Tempus, Jan, et al.
Published: (2026)

Efficient Knowledge Injection in LLMs via Self-Distillation
by: Kujanpää, Kalle, et al.
Published: (2024)

IAPO: Information-Aware Policy Optimization for Token-Efficient Reasoning
by: He, Yinhan, et al.
Published: (2026)

Self-reflecting Large Language Models: A Hegelian Dialectical Approach
by: Abdali, Sara, et al.
Published: (2025)

Rebellious Student: Reversing Teacher Signals for Reasoning Exploration with Self-Distilled RLVR
by: Kim, Jeonghye, et al.
Published: (2026)

AppSelectBench: Application-Level Tool Selection Benchmark
by: Chen, Tianyi, et al.
Published: (2025)

Explain in Your Own Words: Improving Reasoning via Token-Selective Dual Knowledge Distillation
by: Kim, Minsang, et al.
Published: (2026)

ReGUIDE: Data Efficient GUI Grounding via Spatial Reasoning and Search
by: Lee, Hyunseok, et al.
Published: (2025)

Internalize the Temperature: On-Policy Self-Distillation as Policy Reheater for Reinforcement Learning
by: Yang, Xuewei, et al.
Published: (2026)

Efficient Reinforcement Finetuning via Adaptive Curriculum Learning
by: Shi, Taiwei, et al.
Published: (2025)

Flex-Judge: Text-Only Reasoning Unleashes Zero-Shot Multimodal Evaluators
by: Ko, Jongwoo, et al.
Published: (2025)

Self-Refining Language Model Anonymizers via Adversarial Distillation
by: Kim, Kyuyoung, et al.
Published: (2025)

TT-XAI: Trustworthy Clinical Text Explanations via Keyword Distillation and LLM Reasoning
by: Miok, Kristian, et al.
Published: (2025)

MAD-OPD: Breaking the Ceiling in On-Policy Distillation via Multi-Agent Debate
by: Wang, Jianze, et al.
Published: (2026)

Distribution-Aligned Sequence Distillation for Superior Long-CoT Reasoning
by: Yan, Shaotian, et al.
Published: (2026)

SODA: Semi On-Policy Black-Box Distillation for Large Language Models
by: Chen, Xiwen, et al.
Published: (2026)

Structural Rationale Distillation via Reasoning Space Compression
by: Yang, Jialin, et al.
Published: (2026)