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

arXiv:2606.29920 · cs.CL · Submitted 2026-06-29 · Read on arXiv

cs.CL

Submitted: 2026-06-29

Updated: 2026-09-02

Code: https://github.com/THU-KEG/RuVerBench

Terminology

• Agentic Coding — 61× in this paper · explained in 1 episode
• Verification — 39× in this paper · explained in 2 episodes
• Accuracy — 18× in this paper · explained in 1 episode
• Benchmark — 17× in this paper · explained in 2 episodes
• Verifier — 16× in this paper · explained in 2 episodes
• LLM-as-a-Judge — 11× in this paper · explained in 3 episodes
• Provenance — 9× in this paper · explained in 4 episodes
• LLM judge — 7× in this paper · explained in 2 episodes
• Alignment — 3× in this paper · explained in 1 episode
• Consistency — 3× in this paper · explained in 3 episodes
• Reinforcement Learning — 3× in this paper · explained in 4 episodes
• Agentic Evaluation — 2× in this paper · explained in 1 episode
• Agentic System — 1× in this paper · explained in 2 episodes
• Agentic Workflows — 1× in this paper · explained in 1 episode
• Benchmarking — 1× in this paper · explained in 3 episodes
• Computational overhead — 1× in this paper · explained in 2 episodes
• Failure Modes — 1× in this paper · explained in 3 episodes
• Prompt Engineering — 1× in this paper · explained in 4 episodes
• Reinforcement Learning (RL) — 1× in this paper · explained in 25 episodes
• Robustness — 1× in this paper · explained in 5 episodes
• Self-consistency — 1× in this paper · explained in 2 episodes
• Thinking mode — 1× in this paper · explained in 2 episodes

Sources

• OctoBench: Benchmarking Scaffold-Aware Instruction Following in Repository-Grounded Agentic Coding
• TRAJECT-Bench:A Trajectory-Aware Benchmark for Evaluating Agentic Tool Use
• Prometheus: Inducing Fine-grained Evaluation Capability in Language Models
• AlpaGasus: Training A Better Alpaca with Fewer Data
• BrowseComp-Plus: A More Fair and Transparent Evaluation Benchmark of Deep-Research Agent
• RLAIF vs. RLHF: Scaling Reinforcement Learning from Human Feedback with AI Feedback
• DeepResearch Bench II: Diagnosing Deep Research Agents via Rubrics from Expert Reports
• ResearchRubrics: A Benchmark of Prompts and Rubrics For Evaluating Deep Research Agents
• G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment
• JudgeBench: A Benchmark for Evaluating LLM-based Judges
• Large Language Models are not Fair Evaluators
• Self-Instruct: Aligning Language Models with Self-Generated Instructions
• Reframing Instructional Prompts to GPTk's Language
• Long-form factuality in large language models
• AgentSCOPE: Evaluating Contextual Privacy Across Agentic Workflows
• A Comprehensive Survey of Deep Research: Systems, Methodologies, and Applications
• gpt-oss-120b & gpt-oss-20b Model Card
• ResearcherBench: Evaluating Deep AI Research Systems on the Frontiers of Scientific Inquiry
• RubricEval: A Rubric-Level Meta-Evaluation Benchmark for LLM Judges in Instruction Following
• BatchEval: Towards Human-like Text Evaluation

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering