SWE-Bench Mobile: Can Large Language Model Agents Develop Industry-Level Mobile Applications?

• URL: http://arxiv.org/abs/2602.09540v1
• Date: Tue, 10 Feb 2026 08:51:11 GMT
• Title: SWE-Bench Mobile: Can Large Language Model Agents Develop Industry-Level Mobile Applications?
• Authors: Muxin Tian, Zhe Wang, Blair Yang, Zhenwei Tang, Kunlun Zhu, Honghua Dong, Hanchen Li, Xinni Xie, Guangjing Wang, Jiaxuan You,
• Abstract summary: SWE-Bench Mobile is a benchmark for evaluating coding agents on realistic software engineering tasks derived from a production iOS.<n>Unlike existing benchmarks that focus on isolated problems or bug fixes, SWE-Bench Mobile captures the full complexity of industrial development.
• Score: 21.241252187534055
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Can large language model agents develop industry-level mobile applications? We introduce \textbf{SWE-Bench Mobile}, a benchmark for evaluating coding agents on realistic software engineering tasks derived from a production iOS codebase. Unlike existing benchmarks that focus on isolated problems or bug fixes, SWE-Bench Mobile captures the full complexity of industrial development: multi-modal inputs (PRDs and Figma designs), a large-scale mixed Swift/Objective-C codebase, and comprehensive test suites. We evaluate 22 agent-model configurations across four coding agents -- three commercial (Cursor, Codex, Claude Code) and one open-source (OpenCode) -- and find that even the best configurations achieve only 12\% task success rate. Our analysis reveals that (1) agent design matters as much as model capability -- the same model shows up to 6$\times$ performance gap across agents, (2) commercial agents consistently outperform open-source alternatives, and (3) simple ``Defensive Programming'' prompts outperform complex ones by 7.4\%. These findings highlight a significant gap between current agent capabilities and industrial requirements, while providing actionable insights for practitioners and researchers. We release SWE-Bench Mobile as a \textit{hosted benchmark challenge} to prevent data contamination and ensure fair evaluation. The public leaderboard and development toolkit are available at https://swebenchmobile.com.

Related papers

• SWE-Compass: Towards Unified Evaluation of Agentic Coding Abilities for Large Language Models [59.90381306452982]
  evaluating large language models (LLMs) for software engineering has been limited by narrow task coverage, language bias, and insufficient alignment with real-world developer.<n>We introduce SWE-1, a comprehensive benchmark that unifies heterogeneous code-related evaluations into a structured and production-aligned framework.<n>SWE- spans 8 task types, 8 programming scenarios, and 10 programming languages, with 2000 high-quality instances curated from authentic GitHub pull requests.
  arXiv  Detail & Related papers  (2025-11-07T18:01:32Z)
• How can we assess human-agent interactions? Case studies in software agent design [52.953425368394306]
  We make two major steps towards the rigorous assessment of human-agent interactions.<n>We propose PULSE, a framework for more efficient human-centric evaluation of agent designs.<n>We deploy the framework on a large-scale web platform built around the open-source software agent OpenHands.
  arXiv  Detail & Related papers  (2025-10-10T19:04:28Z)
• AgentMesh: A Cooperative Multi-Agent Generative AI Framework for Software Development Automation [0.0]
  We propose a Python-based framework that uses multiple cooperating LLM-powered agents to automate software development tasks.<n>In AgentMesh, specialized agents - a Planner, Coder, Debugger, and Reviewer - work in concert to transform a high-level requirement into fully realized code.
  arXiv  Detail & Related papers  (2025-07-26T10:10:02Z)
• R&D-Agent: An LLM-Agent Framework Towards Autonomous Data Science [70.1638335489284]
  High-level machine learning engineering tasks remain labor-intensive and iterative.<n>We introduce R&D-Agent, a comprehensive, decoupled, and framework that formalizes the machine learning process.<n>R&D-Agent defines the MLE into two phases and six components, turning agent design for MLE into a principled, testable process.
  arXiv  Detail & Related papers  (2025-05-20T06:07:00Z)
• A3: Android Agent Arena for Mobile GUI Agents [46.73085454978007]
  Mobile GUI agents are designed to autonomously perform tasks on mobile devices.<n>Android Agent Arena (A3) is a novel evaluation platform for assessing performance on real-world, in-the-wild tasks.<n>A3 includes 21 widely used general third-party apps and 201 tasks representative of common user scenarios.
  arXiv  Detail & Related papers  (2025-01-02T09:03:56Z)
• Foundations and Recent Trends in Multimodal Mobile Agents: A Survey [72.29426995154088]
  Mobile agents are essential for automating tasks in complex and dynamic mobile environments.<n>Recent advancements enhance real-time adaptability and multimodal interaction.<n>We categorize these advancements into two main approaches: prompt-based methods and training-based methods.
  arXiv  Detail & Related papers  (2024-11-04T11:50:58Z)
• SPA-Bench: A Comprehensive Benchmark for SmartPhone Agent Evaluation [89.24729958546168]
  Smartphone agents are increasingly important for helping users control devices efficiently.<n>We present SPA-Bench, a comprehensive SmartPhone Agent Benchmark designed to evaluate (M)LLM-based agents.
  arXiv  Detail & Related papers  (2024-10-19T17:28:48Z)
• AgentSquare: Automatic LLM Agent Search in Modular Design Space [16.659969168343082]
  Large Language Models (LLMs) have led to a rapid growth of agentic systems capable of handling a wide range of complex tasks.<n>We introduce a new research problem: Modularized LLM Agent Search (MoLAS)
  arXiv  Detail & Related papers  (2024-10-08T15:52:42Z)
• AppAgent v2: Advanced Agent for Flexible Mobile Interactions [57.98933460388985]
  This work introduces a novel LLM-based multimodal agent framework for mobile devices.<n>Our agent constructs a flexible action space that enhances adaptability across various applications.<n>Our results demonstrate the framework's superior performance, confirming its effectiveness in real-world scenarios.
  arXiv  Detail & Related papers  (2024-08-05T06:31:39Z)
• CRAB: Cross-environment Agent Benchmark for Multimodal Language Model Agents [49.68117560675367]
  Crab is the first benchmark framework designed to support cross-environment tasks.<n>Our framework supports multiple devices and can be easily extended to any environment with a Python interface.<n>The experimental results demonstrate that the single agent with GPT-4o achieves the best completion ratio of 38.01%.
  arXiv  Detail & Related papers  (2024-07-01T17:55:04Z)
• MobileAgentBench: An Efficient and User-Friendly Benchmark for Mobile LLM Agents [7.4568642040547894]
  Large language model (LLM)-based mobile agents are increasingly popular due to their capability to interact directly with mobile phone Graphic User Interfaces (GUIs) Despite their promising prospects in both academic and industrial sectors, little research has focused on benchmarking the performance of existing mobile agents. We propose an efficient and user-friendly benchmark, MobileAgentBench, designed to alleviate the burden of extensive manual testing.
  arXiv  Detail & Related papers  (2024-06-12T13:14:50Z)
• Benchmarking Mobile Device Control Agents across Diverse Configurations [19.01954948183538]
  B-MoCA is a benchmark for evaluating and developing mobile device control agents.<n>We benchmark diverse agents, including agents employing large language models (LLMs) or multi-modal LLMs.<n>While these agents demonstrate proficiency in executing straightforward tasks, their poor performance on complex tasks highlights significant opportunities for future research to improve effectiveness.
  arXiv  Detail & Related papers  (2024-04-25T14:56:32Z)

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.