Hugging Face Trending Papers June 17, 2026

Rethinking Reward Supervision: Rubric-Conditioned Self-Distillation

Read the original on Hugging Face Trending Papers →

Post-training of reasoning language models is commonly driven by supervised distillation and reinforcement learning with verifiable rewards. Distillation often relies on chain-of-thought annotations that are expensive to obtain and may themselves be noisy, incomplete, or partially incorrect; even when the final solution is correct, an imperfect rationale can interfere with learning.

Summary generated by The Flow from the publisher's feed. The full article lives at Hugging Face Trending Papers.

arXiv AI

Jun 18

Rethinking Reward Supervision: Rubric-Conditioned Self-Distillation

arXiv:2606. 19327v1 Announce Type: new Abstract: Post-training of reasoning language models is commonly driven by supervised distillation and reinforcement learning with verifiable rewards.

By Siyi Gu, Jialin Chen, Sophia Zhou, Arman Cohan, Rex Ying

llms reinforcement-learning efficiency benchmarks

arXiv Machine Learning

Jul 22

H$^2$SD: Hybrid Hindsight Self-Distillation

arXiv:2607. 18955v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) has substantially improved the reasoning capabilities of large language models on tasks such as mathematical reasoning and code generation.

By Qiye Cai, Yichuan Ma, Linyang Li, Peiji Li, Yongkang Chen, Qipeng Guo, Yicheng Zou, Tao Gui, Xiaocheng Feng, Bing Qin

llms reinforcement-learning efficiency benchmarks

arXiv Machine Learning

Aug 12

Reinforcement Learning-based Semi-supervised Knowledge Distillation with LLM-as-a-Judge

arXiv:2604. 02621v2 Announce Type: replace-cross Abstract: Reinforcement Learning (RL) substantially improves the reasoning capabilities of language models, but most existing RL fine-tuning approaches rely entirely on ground-truth verifiable rewards and thus labeled datasets with verifiable answers.

By Yiyang Shen, Lifu Tu, Weiran Wang

llms reinforcement-learning fine-tuning efficiency

arXiv AI

Aug 5

Rubrics as Privileged Information for Open-Ended Generation

arXiv:2608. 02948v1 Announce Type: cross Abstract: On-policy self-distillation (OPSD), where a single model acts as both student and teacher with different contexts, has shown promise in verifiable domains like math, where hard privileged information (PI) in the form of ground-truth answers structurally constrains valid continuations.

By Deepika Bablani, Ajay Gupta, Wanming Chen

llms reinforcement-learning efficiency benchmarks

arXiv Machine Learning

Jul 31

$\beta$-OPSD: Deriving with Policy Optimization, Training with Self-Distillation

arXiv:2607. 28582v1 Announce Type: new Abstract: On-policy self-distillation (OPSD) is a promising approach to improve reasoning language models, but it remains brittle in practice: making it work reliably often requires substantial engineering effort.

By Jiawei Xu, Minghui Liu, Juzheng Zhang, Tom Goldstein, Furong Huang

llms reinforcement-learning efficiency benchmarks

arXiv AI

Jun 9

Correct Is Not Enough: Training Reasoning Planners with Executor-Grounded Rewards

arXiv:2605. 03862v4 Announce Type: replace Abstract: Reinforcement learning with verifiable rewards has become a common way to improve explicit reasoning in large language models, but final-answer correctness alone does not reveal whether the reasoning trace is faithful, reliable, or useful to the model that consumes it.

By Tianyang Han, Hengyu Shi, Junjie Hu, Xu Yang, Zhiling Wang, Junhao Su

llms reinforcement-learning benchmarks

Related stories

Rethinking Reward Supervision: Rubric-Conditioned Self-Distillation

H$^2$SD: Hybrid Hindsight Self-Distillation

Reinforcement Learning-based Semi-supervised Knowledge Distillation with LLM-as-a-Judge

Rubrics as Privileged Information for Open-Ended Generation

$\beta$-OPSD: Deriving with Policy Optimization, Training with Self-Distillation

Correct Is Not Enough: Training Reasoning Planners with Executor-Grounded Rewards