Hugging Face Trending Papers July 9, 2026

Do You Need a Frontier Model as a Citation Verifier? Benchmarking Rubric LLMs for Deep-Research Source Attribution

Read the original on Hugging Face Trending Papers →

Reinforcement learning increasingly relies on an LLM judge to score each rubric criterion, and that judge acts as the reward model during training. Before such a signal can be trusted, we need to know how capable the judge must be and how biased it is.

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

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 Machine Learning

Aug 4

Does the Competitive Component of Adversarial Self-Play Improve Legal Reasoning? A Controlled Negative Result

arXiv:2608. 01559v1 Announce Type: cross Abstract: Adversarial self-play is an appealing recipe for legal reasoning: have a student model draft an argument, have an adversary attack it, and reward the student when its argument survives the attack.

By Miseog Shawn Kim

reinforcement-learning safety

arXiv AI

Jul 14

STAMP: Provenance-Guided Credit Assignment for Deep Search Agents

arXiv:2607. 11172v1 Announce Type: new Abstract: Reinforcement learning for deep-search agents has largely focused on trajectory-level scoring -- outcome correctness, citation-aware rewards, and evidence coverage.

By Ke Xu, Han Xu, Xinran Chen, Yuqian Wang, Zhixuan Li, Xiaojian Liu, Changwo Wu, Jianqiang Xia, Yuchen Li

agents reinforcement-learning fine-tuning

arXiv Machine Learning

Jul 3

Ask the Right Comparison:Bias-Aware Bayesian Active Top-$k$ Ranking with LLM Judges

arXiv:2607. 02104v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used as cheap, scalable judges that compare candidate outputs pairwise -- to rank responses, select models, or triage papers.

By Jian Xu, Delu Zeng, John Paisley, Qibin Zhao

llms benchmarks safety

arXiv Machine Learning

Jul 8

More Convincing, Not More Correct: Self-Play Reward Hacking of Reference-Free LLM Judges

arXiv:2607. 05904v1 Announce Type: new Abstract: Training a language model against its own reference-free judgments (the premise of self-rewarding, self-play, and LLM-as-a-judge pipelines) assumes a model's verdict on a shown answer tracks correctness.

By Chenyu Zhou

llms reinforcement-learning

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

Related stories

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

Does the Competitive Component of Adversarial Self-Play Improve Legal Reasoning? A Controlled Negative Result

STAMP: Provenance-Guided Credit Assignment for Deep Search Agents

Ask the Right Comparison:Bias-Aware Bayesian Active Top-$k$ Ranking with LLM Judges

More Convincing, Not More Correct: Self-Play Reward Hacking of Reference-Free LLM Judges

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