arXiv Machine Learning June 3, 2026 By Can Lv, Mingju Chen, Heng Chang, Shiji Zhou

Mitigating False Credit Propagation: Probabilistic Graphical Reward Aggregation for Rubric-Based Reinforcement Learning

Read the original on arXiv Machine Learning →

arXiv:2606. 03361v1 Announce Type: new Abstract: Rubric-based rewards are increasingly used for open-ended language model post-training, but criterion-level scores are often aggregated as independent utilities.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

arXiv AI

2d ago

Inducing Reward-Free Judging Rubrics that Reduce Over-Crediting in Agent Evaluation

arXiv:2608. 13564v1 Announce Type: new Abstract: Evaluating language-model agents at scale increasingly relies on a second language model as an automatic judge, because the gold signal, an executable environment reward, is expensive, slow, or unavailable at deployment time.

By Darragh Quinn, David Dylan, Roisin Healy, Fionn Carroll, Maeve Donnelly, Cormac Sheehan

llms agents fine-tuning

arXiv AI

6d ago

Rubric Dropout: A Simple Way to Mitigate Reward Hacking in Rubric-as-Reward RL

arXiv:2608. 11669v1 Announce Type: cross Abstract: Reinforcement learning against rubrics, lists of criteria graded by an LLM judge, has become a standard way to post-train language models on tasks with no deterministic answer.

By Minglai Yang, Xinyu Guo, Utkarsh Tyagi, Mian Zhang, Razvan Dumitru, Sunjie Hou, Yunzhong He, Daniel Yue Zhang, Ying Liu

llms reinforcement-learning benchmarks safety

arXiv AI

Jul 21

Enhancing Rubric-based RL via Self-Distillation

arXiv:2607. 18082v1 Announce Type: cross Abstract: Rubric-based RL has recently shown promise in improving LLMs on open-ended tasks.

By Mingxuan Xia, Yuhang Yang, Chao Ye, Shuai Zhu, Shenzhi Yang, Guangcheng Zhu, Yuhang Zhang, Cheng Peng, Haobo Wang, Siqing Wang

llms reinforcement-learning efficiency benchmarks

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 AI

Jun 18

Learning from Own Solutions: Self-Conditioned Credit Assignment for Reinforcement Learning with Verifiable Rewards

arXiv:2606. 18810v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards (RLVR) has driven substantial progress in training LLMs for reasoning tasks, but representative methods such as GRPO assign uniform credit across all tokens, wasting gradient on routine tokens while under-crediting pivotal reasoning steps.

By Yingyu Shan, Yuhang Guo, Zihao Cheng, Zeming Liu, Xiangrong Zhu, Xinyi Wang, Jiashu Yao, Wei Lin, Hongru Wang, Heyan Huang

llms agents reinforcement-learning efficiency benchmarks

arXiv Machine Learning

Aug 4

CriPO: Enhancing Rubric-based RL via Self-Distillation

arXiv:2607. 18082v3 Announce Type: replace Abstract: Rubric-based RL has recently shown promise in improving LLMs on open-ended tasks.

By Mingxuan Xia, Yuhang Yang, Chao Ye, Shuai Zhu, Shenzhi Yang, Guangcheng Zhu, Yuhang Zhang, Cheng Peng, Haobo Wang, Siqing Wang

llms reinforcement-learning efficiency benchmarks

Related stories

Inducing Reward-Free Judging Rubrics that Reduce Over-Crediting in Agent Evaluation

Rubric Dropout: A Simple Way to Mitigate Reward Hacking in Rubric-as-Reward RL

Enhancing Rubric-based RL via Self-Distillation

Rubrics as Privileged Information for Open-Ended Generation

Learning from Own Solutions: Self-Conditioned Credit Assignment for Reinforcement Learning with Verifiable Rewards

CriPO: Enhancing Rubric-based RL via Self-Distillation