← Back to all news
arXiv Computation and Language By Yangda Peng, Yunjia Qi, Haotian Xia, Guanzhong He, Xintong Shi, Richeng Xuan, Songyuanyi Lu, Yixian Liu, Zhichao Hu, Yuhong Liu, Hao Peng

Can LLM-as-a-Judge Reliably Verify Rubrics in Agentic Scenarios?

Read the original on arXiv Computation and Language →

The paper introduces RuVerBench, a benchmark with 2,458 instances for evaluating the reliability of Large Language Models acting as judges (LaaJ) in verifying rubric compliance within agentic scenarios such as deep research and agentic coding. It systematically meta‑evaluates frontier LLMs, revealing that even the most advanced models perform well yet still produce substantial noise. The study also examines how prompt design, batching, and majority voting affect verification accuracy, noting that weaker models are more prompt‑sensitive, batched verification trades accuracy for efficiency, and majority voting offers diminishing returns.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.

Related stories

arXiv AI
Oct 2

VeriHarness: Scaling Agentic Verification for Long-Horizon Tasks

VeriHarness is a method that enhances verification for large language model agents tackling long‑horizon tasks without needing reference answers at test time. It transforms the base LLM into an agentic verifier by providing a workspace, evidence tools, and reusable verification skills, using disagreement resolution and consensus challenge to evaluate competing claims. Across five benchmarks and two frontier models, VeriHarness outperforms baselines, achieving significant performance gains and demonstrating self‑improvement of verification skills from failure feedback.

By Caiqi Zhang, Rujun Han, Zifeng Wang, Zoey CuiZhu, Nigel Collier, Tomas Pfister, Chen-Yu Lee
llmsagentsbenchmarks
More like this →
arXiv Machine Learning
Oct 9

Evaluating Rubric Generation with Interventional Transfer

The paper introduces Interventional Transfer (IT), a method for evaluating rubric generation by assessing how two rubrics respond to perturbations that cause a pass/fail shift. IT reveals asymmetries in rubrics generated by different LLMs when applied to HealthBench, showing that improvements on one rubric do not reliably transfer to the other. The study contrasts IT with existing evaluation approaches, highlighting its ability to uncover these asymmetries.

By Erik Skalnes, Layne C. Price, Raviteja Anantha, Michael Oberst
llmsbenchmarks
More like this →