Cover Image

OGLS-SD: On-Policy Self-Distillation with Outcome-Guided Logit Steering for LLM Reasoning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Yang, Yuxiao, Wang, Xiaoyun, Zhang, Weitong
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Return-to-Go Is More Than a Number: Q-Guided Alignment for Return-Conditioned Supervised Learning
by: Yang, Yuxiao, et al.
Published: (2026)

Provable and Practical In-Context Policy Optimization for Self-Improvement
by: Yu, Tianrun, et al.
Published: (2026)

Skill-SD: Skill-Conditioned Self-Distillation for Multi-turn LLM Agents
by: Wang, Hao, et al.
Published: (2026)

Logit Distillation on Manifolds: Mapping by Learning
by: Yang, Yiru, et al.
Published: (2026)

Policy Guided Tree Search for Enhanced LLM Reasoning
by: Li, Yang
Published: (2025)

Peak-Controlled Logits Poisoning Attack in Federated Distillation
by: Tang, Yuhan, et al.
Published: (2024)

When Are Teacher Tokens Reliable? Position-Weighted On-Policy Self-Distillation for Reasoning
by: Liu, Xiaogeng, et al.
Published: (2026)

SHRED: Retain-Set-Free Unlearning via Self-Distillation with Logit Demotion
by: Hu, Zizhao, et al.
Published: (2026)

Random Policy Valuation is Enough for LLM Reasoning with Verifiable Rewards
by: He, Haoran, et al.
Published: (2025)

Unearthing Gems from Stones: Policy Optimization with Negative Sample Augmentation for LLM Reasoning
by: Yang, Zhaohui, et al.
Published: (2025)

LLM Reasoning with Process Rewards for Outcome-Guided Steps
by: Rezaei, Mohammad, et al.
Published: (2026)

HINT-SD: Targeted Hindsight Self-Distillation for Long-Horizon Agents
by: Yeo, Woongyeng, et al.
Published: (2026)

UniSD: Towards a Unified Self-Distillation Framework for Large Language Models
by: Jin, Yiqiao, et al.
Published: (2026)

Harmonizing Multi-Objective LLM Unlearning via Unified Domain Representation and Bidirectional Logit Distillation
by: Zhong, Yisheng, et al.
Published: (2026)

Reinforcement-aware Knowledge Distillation for LLM Reasoning
by: Zhang, Zhaoyang, et al.
Published: (2026)

PACED: Distillation and On-Policy Self-Distillation at the Frontier of Student Competence
by: Xu, Yuanda, et al.
Published: (2026)

Logit Dynamics in Softmax Policy Gradient Methods
by: Li, Yingru
Published: (2025)

Steering LLM Reasoning Through Bias-Only Adaptation
by: Sinii, Viacheslav, et al.
Published: (2025)

Prune-OPD: Efficient and Reliable On-Policy Distillation for Long-Horizon Reasoning
by: Yang, Zhicheng, et al.
Published: (2026)

Restoring the Sweet Spot: Pass-Rate Weighted Self-Distillation for LLM Reasoning
by: Liu, Zehao, et al.
Published: (2026)

Unifying Group-Relative and Self-Distillation Policy Optimization via Sample Routing
by: Li, Gengsheng, et al.
Published: (2026)

HDPO: Hybrid Distillation Policy Optimization via Privileged Self-Distillation
by: Ding, Ken
Published: (2026)

Self-Evolving Curriculum for LLM Reasoning
by: Chen, Xiaoyin, et al.
Published: (2025)

BarrierSteer: LLM Safety via Learning Barrier Steering
by: Tran, Thanh Q., et al.
Published: (2026)

APEX: Autonomous Policy Exploration for Self-Evolving LLM Agents
by: Li, Yibo, et al.
Published: (2026)

Uncovering Logit Suppression Vulnerabilities in LLM Safety Alignment
by: Li, Yuxi, et al.
Published: (2024)

TRACE: Distilling Where It Matters via Token-Routed Self On-Policy Alignment
by: Wang, Jiaxuan, et al.
Published: (2026)

SD-MoE: Spectral Decomposition for Effective Expert Specialization
by: Huang, Ruijun, et al.
Published: (2026)

Extreme Region Policy Distillation
by: Chen, Changyu, et al.
Published: (2026)

Aligning Logits Generatively for Principled Black-Box Knowledge Distillation
by: Ma, Jing, et al.
Published: (2022)

LLM-Guided Reinforcement Learning: Addressing Training Bottlenecks through Policy Modulation
by: Tan, Heng, et al.
Published: (2025)

Validity-Calibrated Reasoning Distillation
by: Saadi, Khouloud, et al.
Published: (2026)

From Generic Correlation to Input-Specific Credit in On-Policy Self Distillation
by: Shen, Guobin, et al.
Published: (2026)

Steered LLM Activations are Non-Surjective
by: Mishra, Aayush, et al.
Published: (2026)

Accordion-Thinking: Self-Regulated Step Summaries for Efficient and Readable LLM Reasoning
by: Yang, Zhicheng, et al.
Published: (2026)

POPE: Learning to Reason on Hard Problems via Privileged On-Policy Exploration
by: Qu, Yuxiao, et al.
Published: (2026)

From Atoms to Chains: Divergence-Guided Reasoning Curriculum for Unlabeled LLM Domain Adaptation
by: Wang, Yongqi, et al.
Published: (2026)

Online Policy Distillation with Decision-Attention
by: Yu, Xinqiang, et al.
Published: (2024)

LLM and GNN are Complementary: Distilling LLM for Multimodal Graph Learning
by: Xu, Junjie, et al.
Published: (2024)

OISD: On-Policy Internal Self-Distillation of Language Models
by: Liu, Xinyu, et al.
Published: (2026)