{"total":35,"rows":[{"id":"2604.26752","title":"GLM-5V-Turbo: Toward a Native Foundation Model for Multimodal Agents","created":"2026-04-29","cited_by_count":34,"area":"agents"},{"id":"2601.04126","title":"InfiniteWeb: Scalable Web Environment Synthesis for GUI Agent Training","created":"2026-01-07","cited_by_count":27,"area":"agents"},{"id":"2507.22827","title":"ScreenCoder: Advancing Visual-to-Code Generation for Front-End Automation via Modular Multimodal Agents","created":"2025-07-30","cited_by_count":26,"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":"2509.22097","title":"SecureVibeBench: Benchmarking Secure Vibe Coding of AI Agents via Reconstructing Vulnerability-Introducing Scenarios","created":"2025-09-26","cited_by_count":13,"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":"2505.05283","title":"Software Development Life Cycle Perspective: A Survey of Benchmarks for Code Large Language Models and Agents","created":"2025-05-08","cited_by_count":11,"area":"agents"},{"id":"2511.06251","title":"WebVIA: A Web-based Vision-Language Agentic Framework for Interactive and Verifiable UI-to-Code Generation","created":"2025-11-09","cited_by_count":10,"area":"agents"},{"id":"2511.15567","title":"Computer-Use Agents as Judges for Generative User Interface","created":"2025-11-19","cited_by_count":9,"area":"agents"},{"id":"2608.13560","title":"AutoDesign: Meta-Harness Optimization for Long-Horizon Agentic Design","created":"2026-08-13","cited_by_count":9,"area":"agents"},{"id":"2603.27703","title":"KAT-Coder-V2 Technical Report","created":"2026-03-29","cited_by_count":8,"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":"2502.18525","title":"Programming with Pixels: Can Computer-Use Agents do Software Engineering?","created":"2025-02-24","cited_by_count":4,"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":"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":"2603.22744","title":"LH-Bench: Skill-Grounded Evaluation of Long-Horizon Agents on Subjective Enterprise Tasks","created":"2026-03-24","cited_by_count":3,"area":"agents"},{"id":"2605.26144","title":"VISTA: An End-to-End Benchmark for Visual Spec-to-Web-App Coding Agents","created":"2026-05-22","cited_by_count":3,"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":"2605.25160","title":"ScaleWoB: Guiding GUI Agents with Coding Agents via Large-Scale Environmental Synthesis","created":"2026-05-24","cited_by_count":2,"area":"agents"},{"id":"2602.12311","title":"Perceptual Self-Reflection in Agentic Physics Simulation Code Generation","created":"2026-02-12","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":"2608.00548","title":"DrawAI: Agentic Benchmark and Workflow for Making Raster Images Editable","created":"2026-08-01","cited_by_count":1,"area":"agents"},{"id":"2608.03298","title":"SeaSlides: Semantic Abstraction Layer for Agentic Slide Generation","created":"2026-08-04","cited_by_count":1,"area":"agents"},{"id":"2609.06758","title":"Agentic Visual Generation: From Generative Models to Agentic Control","created":"2026-09-06","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":"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":"2608.29889","title":"VibeJam: A User Study Platform for Web Development with Agents","created":"2026-08-30","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":"2609.15078","title":"Enabling Creative Exploration for Vibe Design Agents","created":"2026-09-14","cited_by_count":0,"area":"agents"},{"id":"2609.18805","title":"ProgramDistill: From Interactive Web Apps to Verifiable Reference-Guided SWE Tasks","created":"2026-09-16","cited_by_count":0,"area":"agents"},{"id":"2609.18844","title":"ReFigBench: Benchmarking Scientific Figure Reconstruction as Editable PowerPoint Artifacts","created":"2026-09-16","cited_by_count":0,"area":"agents"}],"next_cursor":null}