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

• URL: http://arxiv.org/abs/2606.29920v1
• Date: Mon, 29 Jun 2026 07:57:23 GMT
• Title: Can LLM-as-a-Judge Reliably Verify Rubrics in Agentic Scenarios?
• Abstract summary: We introduce RuVerBench, the first benchmark for assessing LaaJ reliability in rubric verification for agentic scenarios.<n>RuVerBench covers two prevalent agentic domains, deep research and agentic coding, with 2,458 instances, each containing a model-generated output, a rubric, and a human-annotated label.<n>We find that weaker models are more sensitive to prompt variations, batched verification presents a trade-off between accuracy and efficiency, and majority voting yields effective but diminishing returns.
• Score: 43.35973462024656
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Rubric-based scoring has become a widely used paradigm in model evaluation, typically with LLM-as-a-Judge (LaaJ) for rubric scoring. However, the reliability of LaaJ for rubric scoring remains underexplored. This concern is especially pronounced in agentic scenarios, where long, complex outputs further challenge reliable scoring. To address this, we conduct a systematic meta-evaluation of LaaJ reliability for rubric verification. We introduce RuVerBench, the first benchmark for assessing LaaJ reliability in rubric verification for agentic scenarios. RuVerBench covers two prevalent agentic domains, deep research and agentic coding, with 2,458 instances, each containing a model-generated output, a rubric, and a human-annotated label indicating whether the output satisfies the rubric. Using RuVerBench, we evaluate numerous frontier LLMs and find that even the most advanced models achieve strong performance but still exhibit substantial noise. We further analyze the impact of key LaaJ strategies, including prompt design, batching, and majority voting, on rubric verification. We find that weaker models are more sensitive to prompt variations, batched verification presents a trade-off between accuracy and efficiency, and majority voting yields effective but diminishing returns. We have released our dataset and code to facilitate future research: https://github.com/THU-KEG/RuVerBench.

Related papers

• Can LLMs Write Reliable Rubrics? A Meta-Evaluation for Experiment Reproduction [38.170020271877085]
  We present the first systematic meta-evaluation of LLM-generated rubrics for paper reproduction.<n>We reformulate rubrics into a checklist-style format and evaluate four generation settings across two backbone models.
  arXiv  Detail & Related papers  (2026-07-14T14:52:42Z)
• AJ-Bench: Benchmarking Agent-as-a-Judge for Environment-Aware Evaluation [71.49152943451328]
  We introduce a benchmark AJ-Bench to evaluate Agent-as-a-Judge across three domains-search, data systems, and graphical user interfaces-comprising 155 tasks and 516 annotated trajectories.<n>Experiments demonstrate consistent performance gains over LLM-as-a-Judge baselines, while also revealing substantial open challenges in agent-based verification.
  arXiv  Detail & Related papers  (2026-04-20T13:23:38Z)
• RubricRAG: Towards Interpretable and Reliable LLM Evaluation via Domain Knowledge Retrieval for Rubric Generation [11.21565372620296]
  Large language models (LLMs) are increasingly evaluated and sometimes trained using automated graders that output scalar scores or preferences.<n>This lack of interpretability limits their usefulness for model development, dataset curation, and high-stakes deployment.<n>We introduce a simple strategy,RAG, which retrieves domain knowledge via rubrics at inference time from related queries.
  arXiv  Detail & Related papers  (2026-03-21T17:10:14Z)
• Beyond Blind Spots: Analytic Hints for Mitigating LLM-Based Evaluation Pitfalls [2.4484932263697234]
  Large Language Models are increasingly deployed as judges (LaaJ) in code generation pipelines.<n>LaaJs tend to overlook domain specific issues raising concerns about their reliability in critical evaluation tasks.<n>We develop a lightweight analytic checker tool that flags over 30 domain specific issues observed in practice.<n>We use its outputs as analytic hints, dynamically injecting them into the judges prompt to encourage LaaJ to revisit aspects it may have overlooked.
  arXiv  Detail & Related papers  (2025-12-18T07:43:48Z)
• CompassVerifier: A Unified and Robust Verifier for LLMs Evaluation and Outcome Reward [50.97588334916863]
  We develop CompassVerifier, an accurate and robust lightweight verifier model for evaluation and outcome reward.<n>It demonstrates multi-domain competency spanning math, knowledge, and diverse reasoning tasks, with the capability to process various answer types.<n>We introduce VerifierBench benchmark comprising model outputs collected from multiple data sources, augmented through manual analysis of metaerror patterns to enhance CompassVerifier.
  arXiv  Detail & Related papers  (2025-08-05T17:55:24Z)
• Verifying the Verifiers: Unveiling Pitfalls and Potentials in Fact Verifiers [59.168391398830515]
  We evaluate 12 pre-trained LLMs and one specialized fact-verifier, using a collection of examples from 14 fact-checking benchmarks.<n>We highlight the importance of addressing annotation errors and ambiguity in datasets.<n> frontier LLMs with few-shot in-context examples, often overlooked in previous works, achieve top-tier performance.
  arXiv  Detail & Related papers  (2025-06-16T10:32:10Z)
• Bi'an: A Bilingual Benchmark and Model for Hallucination Detection in Retrieval-Augmented Generation [6.549143816134529]
  We introduce bftextBi'an, a novel framework featuring a bilingual benchmark dataset and lightweight judge models.<n>The dataset supports rigorous evaluation across multiple RAG scenarios, while the judge models are fine-tuned from compact open-source LLMs.
  arXiv  Detail & Related papers  (2025-02-26T15:12:59Z)
• Are Your LLMs Capable of Stable Reasoning? [38.03049704515947]
  We introduce G-Pass@$k$, a novel evaluation metric that continuously assesses model performance across multiple sampling attempts.<n>We employ G-Pass@$k$ in conjunction with state-of-the-art large language models to provide comprehensive insights into their potential capabilities and operational consistency.
  arXiv  Detail & Related papers  (2024-12-17T18:12:47Z)
• Benchmarking Large Language Models in Retrieval-Augmented Generation [53.504471079548]
  We systematically investigate the impact of Retrieval-Augmented Generation on large language models. We analyze the performance of different large language models in 4 fundamental abilities required for RAG. We establish Retrieval-Augmented Generation Benchmark (RGB), a new corpus for RAG evaluation in both English and Chinese.
  arXiv  Detail & Related papers  (2023-09-04T08:28:44Z)
• Revisiting Out-of-distribution Robustness in NLP: Benchmark, Analysis, and LLMs Evaluations [111.88727295707454]
  This paper reexamines the research on out-of-distribution (OOD) robustness in the field of NLP. We propose a benchmark construction protocol that ensures clear differentiation and challenging distribution shifts. We conduct experiments on pre-trained language models for analysis and evaluation of OOD robustness.
  arXiv  Detail & Related papers  (2023-06-07T17:47:03Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.