# Benchmarking LLM Judges for Mobile Agent Evaluation

arXiv: https://arxiv.org/abs/2608.11434 · HTML: https://mlsanity.com/paper/2608.11434/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use.
- Builds on 37 of its 45 references that are in the map.
- First posted on arXiv 11 Aug 2026.

## Placed in

- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)

## Builds on (most cited first, 30 of 37)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Constitutional AI: Harmlessness from AI Feedback](https://mlsanity.com/paper/2212.08073/) (2022)
- [HybridFlow: A Flexible and Efficient RLHF Framework](https://mlsanity.com/paper/2409.19256/) (2024)
- [WebArena: A Realistic Web Environment for Building Autonomous Agents](https://mlsanity.com/paper/2307.13854/) (2023)
- [A Survey on LLM-as-a-Judge](https://mlsanity.com/paper/2411.15594/) (2024)
- [Mind2Web: Towards a Generalist Agent for the Web](https://mlsanity.com/paper/2306.06070/) (2023)
- [OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments](https://mlsanity.com/paper/2404.07972/) (2024)
- [Scaling Laws for Reward Model Overoptimization](https://mlsanity.com/paper/2210.10760/) (2022)
- [AndroidWorld: A Dynamic Benchmarking Environment for Autonomous Agents](https://mlsanity.com/paper/2405.14573/) (2024)
- [GLM-4.5V and GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning](https://mlsanity.com/paper/2507.01006/) (2025)
- [LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods](https://mlsanity.com/paper/2412.05579/) (2024)
- [JudgeLM: Fine-tuned Large Language Models are Scalable Judges](https://mlsanity.com/paper/2310.17631/) (2023)
- [WebRL: Training LLM Web Agents via Self-Evolving Online Curriculum Reinforcement Learning](https://mlsanity.com/paper/2411.02337/) (2024)
- [Agent-as-a-Judge: Evaluate Agents with Agents](https://mlsanity.com/paper/2410.10934/) (2024)
- [DigiRL: Training In-The-Wild Device-Control Agents with Autonomous Reinforcement Learning](https://mlsanity.com/paper/2406.11896/) (2024)
- [On the Effects of Data Scale on UI Control Agents](https://mlsanity.com/paper/2406.03679/) (2024)
- [An Illusion of Progress? Assessing the Current State of Web Agents](https://mlsanity.com/paper/2504.01382/) (2025)
- [LLM Critics Help Catch LLM Bugs](https://mlsanity.com/paper/2407.00215/) (2024)
- [Autonomous Evaluation and Refinement of Digital Agents](https://mlsanity.com/paper/2404.06474/) (2024)
- [Preference Leakage: A Contamination Problem in LLM-as-a-judge](https://mlsanity.com/paper/2502.01534/) (2025)
- [AgentRewardBench: Evaluating Automatic Evaluations of Web Agent Trajectories](https://mlsanity.com/paper/2504.08942/) (2025)
- [AndroidLab: Training and Systematic Benchmarking of Android Autonomous Agents](https://mlsanity.com/paper/2410.24024/) (2024)
- [Trust or Escalate: LLM Judges with Provable Guarantees for Human Agreement](https://mlsanity.com/paper/2407.18370/) (2024)
- [SPA-Bench: A Comprehensive Benchmark for SmartPhone Agent Evaluation](https://mlsanity.com/paper/2410.15164/) (2024)
- [Understanding the Weakness of Large Language Model Agents within a Complex Android Environment](https://mlsanity.com/paper/2402.06596/) (2024)
- [NNetNav: Unsupervised Learning of Browser Agents Through Environment Interaction in the Wild](https://mlsanity.com/paper/2410.02907/) (2024)
- [Benchmarking Mobile Device Control Agents across Diverse Configurations](https://mlsanity.com/paper/2404.16660/) (2024)

## Built on by (most cited first, 1 of 1)

- [Finding Blind Spots in AppWorld and WorkArena Task Verifiers](https://mlsanity.com/paper/2610.09142/) (2026)

## Abstract (arXiv)

Mobile agent benchmarks increasingly rely on LLM-based judges to evaluate task completion, yet the reliability of these judges on mobile agent trajectories remains largely unexamined. We introduce MobileJudgeBench, a benchmark for systematically evaluating LLM-as-judge methods on mobile agent trajectories. Our benchmark comprises 931 human-annotated trajectories spanning 6 mobile agent benchmarks, 4 agent models, and 68 apps. We evaluate 6 judge methods (five adapted from SPA-Bench, A3 with two modes, AndroidArena, and AgentRewardBench, plus a simple baseline we design) across multiple LLM backends. Our experiments reveal three key findings. First, a simple baseline judge with sampled screenshots is competitive with, and often exceeds, purpose-built methods, indicating that more elaborate judge pipelines do not consistently improve judge quality; among competitive methods, the LLM backbone is the primary driver. Second, benchmark quality metrics reliably predict real-world judge utility: they correlate with both agent ranking fidelity for evaluation and downstream performance when judges serve as reward signals for on-policy reinforcement learning. Third, failure analysis across two LLM backends uncovers qualitatively opposite failure profiles, one conservative and the other permissive, linked to the backbone's precision-recall characteristics.