EPISODE · Apr 3, 2026 · 23 MIN
Vision2Web: A Hierarchical Benchmark for Visual Website Development with Agent Verification
from Daily Paper Cast · host Jingwen Liang, Gengyu Wang
🤗 Upvotes: 33 | cs.SE, cs.AI Authors: Zehai He, Wenyi Hong, Zhen Yang, Ziyang Pan, Mingdao Liu, Xiaotao Gu, Jie Tang Title: Vision2Web: A Hierarchical Benchmark for Visual Website Development with Agent Verification Arxiv: http://arxiv.org/abs/2603.26648v2 Abstract: Recent advances in large language models have improved the capabilities of coding agents, yet systematic evaluation of complex, end-to-end website development remains limited. To address this gap, we introduce Vision2Web, a hierarchical benchmark for visual website development, spanning from static UI-to-code generation, interactive multi-page frontend reproduction, to long-horizon full-stack website development. The benchmark is constructed from real-world websites and comprises a total of 193 tasks across 16 categories, with 918 prototype images and 1,255 test cases. To support flexible, thorough and reliable evaluation, we propose workflow-based agent verification paradigm based on two complementary components: a GUI agent verifier and a VLM-based judge. We evaluate multiple visual language models instantiated under different coding-agent frameworks, revealing substantial performance gaps at all task levels, with state-of-the-art models still struggling on full-stack development.
What this episode covers
🤗 Upvotes: 33 | cs.SE, cs.AI Authors: Zehai He, Wenyi Hong, Zhen Yang, Ziyang Pan, Mingdao Liu, Xiaotao Gu, Jie Tang Title: Vision2Web: A Hierarchical Benchmark for Visual Website Development with Agent Verification Arxiv: http://arxiv.org/abs/2603.26648v2 Abstract: Recent advances in large language models have improved the capabilities of coding agents, yet systematic evaluation of complex, end-to-end website development remains limited. To address this gap, we introduce Vision2Web, a hierarchical benchmark for visual website development, spanning from static UI-to-code generation, interactive multi-page frontend reproduction, to long-horizon full-stack website development. The benchmark is constructed from real-world websites and comprises a total of 193 tasks across 16 categories, with 918 prototype images and 1,255 test cases. To support flexible, thorough and reliable evaluation, we propose workflow-based agent verification paradigm based on two complementary components: a GUI agent verifier and a VLM-based judge. We evaluate multiple visual language models instantiated under different coding-agent frameworks, revealing substantial performance gaps at all task levels, with state-of-the-art models still struggling on full-stack development.
NOW PLAYING
Vision2Web: A Hierarchical Benchmark for Visual Website Development with Agent Verification
No transcript for this episode yet
Similar Episodes
No similar episodes found.