{"total":23,"rows":[{"id":"2507.04952","title":"ArtifactsBench: Bridging the Visual-Interactive Gap in LLM Code Generation Evaluation","created":"2025-07-07","cited_by_count":42,"area":null},{"id":"2601.02430","title":"WebCoderBench: Benchmarking Web Application Generation with Comprehensive and Interpretable Evaluation Metrics","created":"2026-01-05","cited_by_count":18,"area":null},{"id":"2508.14104","title":"You Don't Know Until You Click:Automated GUI Testing for Production-Ready Software Evaluation","created":"2025-08-17","cited_by_count":12,"area":null},{"id":"2509.24709","title":"IWR-Bench: Can LVLMs reconstruct interactive webpage from a user interaction video?","created":"2025-09-29","cited_by_count":12,"area":null},{"id":"2601.20882","title":"DevOps-Gym: Benchmarking AI Agents in Software DevOps Cycle","created":"2026-01-27","cited_by_count":11,"area":null},{"id":"2606.01869","title":"WorldCoder-Bench: Benchmarking Physically Grounded 3D World Synthesis","created":"2026-06-01","cited_by_count":9,"area":null},{"id":"2603.09652","title":"MiniAppBench: Evaluating the Shift from Text to Interactive HTML Responses in LLM-Powered Assistants","created":"2026-03-10","cited_by_count":8,"area":null},{"id":"2606.15932","title":"Beyond NL2Code: A Structured Survey of Multimodal Code Intelligence","created":"2026-06-14","cited_by_count":6,"area":null},{"id":"2510.07740","title":"AppForge: From Assistant to Independent Developer -- Are GPTs Ready for Software Development?","created":"2025-10-09","cited_by_count":4,"area":null},{"id":"2508.07180","title":"Code2Bench: Scaling Source and Rigor for Dynamic Benchmark Construction","created":"2025-08-10","cited_by_count":3,"area":null},{"id":"2510.15306","title":"WebGen-V Bench: Structured Representation for Enhancing Visual Design in LLM-based Web Generation and Evaluation","created":"2025-10-17","cited_by_count":3,"area":null},{"id":"2605.30000","title":"Cookie-Bench: Continuous On-screen Key Interaction Evaluation for Web Generation","created":"2026-05-28","cited_by_count":3,"area":null},{"id":"2606.00750","title":"I-WebGenBench : Evaluating Interactivity in LLM-Generated Scientific Web Applications","created":"2026-05-30","cited_by_count":3,"area":null},{"id":"2605.15222","title":"PerfCodeBench: Benchmarking LLMs for System-Level High-Performance Code Optimization","created":"2026-05-13","cited_by_count":2,"area":null},{"id":"2510.06223","title":"A Multimodal GUI Architecture for Interfacing with LLM-Based Conversational Assistants","created":"2025-08-31","cited_by_count":1,"area":null},{"id":"2604.19750","title":"Coding with Eyes: Visual Feedback Unlocks Reliable GUI Code Generating and Debugging","created":"2026-03-14","cited_by_count":1,"area":null},{"id":"2608.03689","title":"LiveEvalBench: Toward Open-World Evaluation for Web Generation","created":"2026-08-04","cited_by_count":1,"area":null},{"id":"2608.23067","title":"Signal or Noise? A Benchmark Study of Agent Skills in Web Development","created":"2026-08-24","cited_by_count":1,"area":null},{"id":"2507.19904","title":"CrossPL: Evaluating Large Language Models on Cross Programming Language Code Generation","created":"2025-07-26","cited_by_count":0,"area":null},{"id":"2509.09717","title":"Testing chatbots on the creation of encoders for audio conditioned image generation","created":"2025-09-09","cited_by_count":0,"area":null},{"id":"2604.22306","title":"BLAST: Benchmarking LLMs with ASP-based Structured Testing","created":"2026-04-24","cited_by_count":0,"area":null},{"id":"2609.15387","title":"WebCraftBench: Evaluating Web Application Generation from a Software Testing Perspective","created":"2026-09-14","cited_by_count":0,"area":null},{"id":"2610.04981","title":"TeleGen: Improving LLM-Based Web Application Generation via Runtime Telemetry","created":"2026-10-04","cited_by_count":0,"area":null}],"next_cursor":null}