{"total":18,"rows":[{"id":"2511.00391","title":"VinciCoder: Unifying Multimodal Code Generation via Coarse-to-fine Visual Reinforcement Learning","created":"2025-11-01","cited_by_count":21,"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":"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":"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":"2606.03220","title":"WebRISE: Requirement-Induced State Evaluation for MLLM-Generated Web Artifacts","created":"2026-06-02","cited_by_count":2,"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":"2608.29387","title":"EvoGenUI-Bench: Evaluating LLMs as Multi-Turn Generative UI Assistants","created":"2026-08-29","cited_by_count":1,"area":null},{"id":"2606.15693","title":"Imperfect Visual Verification for Code Edition : A Case Study on TikZ","created":"2026-04-09","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":"2608.10567","title":"DashArena: Benchmarking LLMs on Interactive Analytic Dashboard Generation","created":"2026-08-11","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":"2610.04253","title":"Spec2Game: Can LLMs Generate Complete Playable Games from Detailed Specifications?","created":"2026-10-03","cited_by_count":0,"area":null},{"id":"2610.18860","title":"AesCode: Aesthetic Code Generation with Decoupled Cross-Modal Rewards","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}