{"total":27,"rows":[{"id":"2601.04126","title":"InfiniteWeb: Scalable Web Environment Synthesis for GUI Agent Training","created":"2026-01-07","cited_by_count":27,"area":"agents"},{"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":"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":"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":"2603.10505","title":"Safe and Scalable Web Agent Learning via Recreated Websites","created":"2026-03-11","cited_by_count":11,"area":"agents"},{"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":"2604.15309","title":"MM-WebAgent: A Hierarchical Multimodal Web Agent for Webpage Generation","created":"2026-04-16","cited_by_count":5,"area":"agents"},{"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":"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":"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":"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":"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":"2609.22000","title":"RecreationWorld: Scalable and Verifiable Environments for Hybrid Computer-Use Agents","created":"2026-09-18","cited_by_count":1,"area":"agents"},{"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":"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":"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":"2609.32600","title":"CUA-SWE: When Computer-Use Agents Meet Visual Software Engineering","created":"2026-09-26","cited_by_count":0,"area":"agents"},{"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}