{"total":72,"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":"2601.04126","title":"InfiniteWeb: Scalable Web Environment Synthesis for GUI Agent Training","created":"2026-01-07","cited_by_count":27,"area":"agents"},{"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":"2603.26648","title":"Vision2Web: A Hierarchical Benchmark for Visual Website Development with Agent Verification","created":"2026-03-27","cited_by_count":16,"area":"agents"},{"id":"2509.22644","title":"WebGen-Agent: Enhancing Interactive Website Generation with Multi-Level Feedback and Step-Level Reinforcement Learning","created":"2025-09-26","cited_by_count":15,"area":"lr"},{"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":"2511.18538","title":"From Code Foundation Models to Agents and Applications: A Comprehensive Survey and Practical Guide to Code Intelligence","created":"2025-11-23","cited_by_count":15,"area":"agents"},{"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":"2506.16136","title":"Seeing is Fixing: Cross-Modal Reasoning with Multimodal LLMs for Visual Software Issue Fixing","created":"2025-06-19","cited_by_count":12,"area":"lr"},{"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":"2605.17637","title":"WebGameBench: Requirement-to-Application Evaluation for Coding Agents via Browser-Native Games","created":"2026-05-17","cited_by_count":12,"area":"agents"},{"id":"2601.21968","title":"OVD: On-policy Verbal Distillation","created":"2026-01-29","cited_by_count":11,"area":"lr"},{"id":"2603.10505","title":"Safe and Scalable Web Agent Learning via Recreated Websites","created":"2026-03-11","cited_by_count":11,"area":"agents"},{"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":"2510.09361","title":"BLINK-Twice: You see, but do you observe? A Reasoning Benchmark on Visual Perception","created":"2025-10-10","cited_by_count":9,"area":"lr"},{"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":"2603.13391","title":"WebVR: Benchmarking Multimodal LLMs for WebPage Recreation from Videos via Human-Aligned Visual Rubrics","created":"2026-03-11","cited_by_count":8,"area":"mllm"},{"id":"2509.25297","title":"Automatically Generating Web Applications from Requirements Via Multi-Agent Test-Driven Development","created":"2025-09-29","cited_by_count":7,"area":"agents"},{"id":"2607.08938","title":"Better Harnesses, Smaller Models: Building 90% Cheaper Agents via Automated Harness Adaptation","created":"2026-07-09","cited_by_count":7,"area":"agents"},{"id":"2604.18224","title":"WebCompass: Towards Multimodal Web Coding Evaluation for Code Language Models","created":"2026-04-20","cited_by_count":6,"area":"agents"},{"id":"2606.15932","title":"Beyond NL2Code: A Structured Survey of Multimodal Code Intelligence","created":"2026-06-14","cited_by_count":6,"area":null},{"id":"2604.15309","title":"MM-WebAgent: A Hierarchical Multimodal Web Agent for Webpage Generation","created":"2026-04-16","cited_by_count":5,"area":"agents"},{"id":"2508.19532","title":"Alignment with Fill-In-the-Middle for Enhancing Code Generation","created":"2025-08-27","cited_by_count":4,"area":"alignment"},{"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":"2603.25226","title":"WebTestBench: Evaluating Computer-Use Agents towards End-to-End Automated Web Testing","created":"2026-03-26","cited_by_count":4,"area":"agents"},{"id":"2603.25804","title":"RealChart2Code: Advancing Chart-to-Code Generation with Real Data and Multi-Task Evaluation","created":"2026-03-26","cited_by_count":4,"area":"mllm"},{"id":"2605.17526","title":"SaaSBench: Exploring the Boundaries of Coding Agents in Long-Horizon Enterprise SaaS Engineering","created":"2026-05-17","cited_by_count":4,"area":"agents"},{"id":"2606.05920","title":"Asuka-Bench: Benchmarking Code Agents on Underspecified User Intent and Multi-Round Refinement","created":"2026-06-04","cited_by_count":4,"area":"agents"},{"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":"2602.03798","title":"FullStack-Agent: Enhancing Agentic Full-Stack Web Coding via Development-Oriented Testing and Repository Back-Translation","created":"2026-02-03","cited_by_count":2,"area":"agents"},{"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":"2605.17439","title":"DiagEval: Trajectory-Conditioned Diagnosis for Reliable Software Evaluation with GUI Agents","created":"2026-05-17","cited_by_count":2,"area":"agents"},{"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":"2604.25914","title":"DV-World: Benchmarking Data Visualization Agents in Real-World Scenarios","created":"2026-04-28","cited_by_count":1,"area":"agents"},{"id":"2604.27419","title":"InteractWeb-Bench: Can Multimodal Agent Escape Blind Execution in Interactive Website Generation?","created":"2026-04-30","cited_by_count":1,"area":"agents"},{"id":"2606.00154","title":"Benchmarking Multimodal LLMs on Code Generation for Complex Interactive Webpages","created":"2026-05-29","cited_by_count":1,"area":"lr"},{"id":"2608.06474","title":"WebGrader: Training LLMs for Web Development with Self-Evolving Programmatic Grader","created":"2026-08-06","cited_by_count":1,"area":"synth"},{"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":"2609.22000","title":"RecreationWorld: Scalable and Verifiable Environments for Hybrid Computer-Use Agents","created":"2026-09-18","cited_by_count":1,"area":"agents"},{"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":"2511.20656","title":"Context-Aware Visual Prompting: Automating Geospatial Web Dashboards with Large Language Models and Agent Self-Validation for Decision Support","created":"2025-10-10","cited_by_count":0,"area":"agents"},{"id":"2605.04637","title":"SWE-WebDevBench: Evaluating Coding Agent Application Platforms as Virtual Software Agencies","created":"2026-05-06","cited_by_count":0,"area":"agents"},{"id":"2605.05828","title":"From Chat to Interview: Agentic Requirements Elicitation with an Experience Ontology","created":"2026-05-07","cited_by_count":0,"area":"agents"},{"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":"2606.17727","title":"LongWebBench: Evaluating Structural and Functional Webpage Generation in Long-Horizon Settings","created":"2026-06-16","cited_by_count":0,"area":"mllm"},{"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":"2608.03474","title":"MT-Web2Code: Benchmarking Coding Agents on Multi-Turn Regional Reconstruction and Localized Modification","created":"2026-08-04","cited_by_count":0,"area":"mllm"},{"id":"2608.27902","title":"LandingAgent: A Reference-Annotated Dataset and Agentic Generation Framework for Landing Pages","created":"2026-08-28","cited_by_count":0,"area":"agents"},{"id":"2608.28795","title":"The reach of a verification tool decides its value: A controlled study of verification surface, artifact quality, and cost in AI coding agents","created":"2026-08-28","cited_by_count":0,"area":"agents"},{"id":"2608.29310","title":"Super Library Agent: Joint Generation and Maintenance of Multiple Applications Beyond the Single Codebase","created":"2026-08-29","cited_by_count":0,"area":"agents"},{"id":"2608.30530","title":"WebWorld: The Browser as a World Model for Self-Improving Web Code","created":"2026-08-31","cited_by_count":0,"area":"wm"},{"id":"2609.00081","title":"Framework and Benchmark for Code-Driven Agentic Testing in Web Development","created":"2026-08-31","cited_by_count":0,"area":"agents"},{"id":"2609.02088","title":"Rendering-in-the-Loop: An Execution-Driven Agent for Interactive Web Development","created":"2026-09-02","cited_by_count":0,"area":"agents"},{"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":"2609.32600","title":"CUA-SWE: When Computer-Use Agents Meet Visual Software Engineering","created":"2026-09-26","cited_by_count":0,"area":"agents"},{"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},{"id":"2610.16402","title":"EvoWeb: A Benchmark for Coding Agents on Evolving Web Applications","created":"2026-10-12","cited_by_count":0,"area":"agents"}],"next_cursor":null}