{"total":33,"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":"2511.08195","title":"UI2Code^N: UI-to-Code Generation as Interactive Visual Optimization","created":"2025-11-11","cited_by_count":15,"area":null},{"id":"2601.04203","title":"FronTalk: Benchmarking Front-End Development as Conversational Code Generation with Multi-Modal Feedback","created":"2025-12-05","cited_by_count":14,"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":"2605.07442","title":"GameGen-Verifier: Parallel Keypoint-Based Verification for LLM-Generated Games via Runtime State Injection","created":"2026-05-08","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":"2510.09724","title":"InteractScience: Programmatic and Visually-Grounded Evaluation of Interactive Scientific Demonstration Code Generation","created":"2025-10-10","cited_by_count":4,"area":null},{"id":"2505.05026","title":"Do MLLMs Capture How Interfaces Guide User Behavior? A Benchmark for Multimodal UI/UX Design Understanding","created":"2025-05-08","cited_by_count":3,"area":null},{"id":"2508.20410","title":"UI-Bench: A Benchmark for Evaluating Design Capabilities of AI Text-to-App Tools","created":"2025-08-28","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":"2604.20398","title":"WebGen-R1: Incentivizing Large Language Models to Generate Functional and Aesthetic Websites with Reinforcement Learning","created":"2026-04-22","cited_by_count":2,"area":null},{"id":"2605.26807","title":"HTMLCure: Turning Browser Experience into State Guided Repair for Interactive HTML","created":"2026-05-26","cited_by_count":2,"area":null},{"id":"2510.15842","title":"Paper2Web: Let's Make Your Paper Alive!","created":"2025-10-17","cited_by_count":1,"area":null},{"id":"2602.04894","title":"Extracting Recurring Vulnerabilities from Black-Box LLM-Generated Software","created":"2026-02-02","cited_by_count":1,"area":null},{"id":"2602.21143","title":"A Benchmark for Deep Information Synthesis","created":"2026-02-24","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":"2608.09573","title":"VideoVIBE: A Video-Grounded Diagnostic Benchmark for One-Shot Interactive Website Generation","created":"2026-08-10","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":"2608.29387","title":"EvoGenUI-Bench: Evaluating LLMs as Multi-Turn Generative UI Assistants","created":"2026-08-29","cited_by_count":1,"area":null},{"id":"2609.21293","title":"GameASG-Bench: Benchmarking Autonomous Software Generation for Game Development","created":"2026-09-18","cited_by_count":1,"area":null},{"id":"2609.36903","title":"MultiTalk: Scaling Full-Duplex Speech Models to Long, Multi-Party, Bilingual Conversation","created":"2026-09-29","cited_by_count":1,"area":null},{"id":"2605.30358","title":"QASM-Eval: A Dataset to Train and Evaluate LLMs on OpenQASM-3 Beyond Quantum Circuits","created":"2026-04-28","cited_by_count":0,"area":null},{"id":"2607.06306","title":"UI2App: Benchmarking Visual Interaction Inference in Executable Web Application Generation","created":"2026-07-07","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":"2609.22308","title":"GameReplica: A Benchmark for Black-Box Visual Game Replication by Vision-Language Agents","created":"2026-09-15","cited_by_count":0,"area":null},{"id":"2609.34854","title":"AUV-Bench: Aesthetic Understanding and Generation Evaluation for User Interfaces","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2610.04381","title":"Beyond Plausibility: Verifiable Fine-Grained Image Editing on Structured Assets","created":"2026-10-03","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},{"id":"2610.13022","title":"Don't Guess, Just Ask: Evaluating Interactive Requirement Clarification for Repository-Level Software Development","created":"2026-10-09","cited_by_count":0,"area":null}],"next_cursor":null}