Newest papers

RefCraft: Benchmarking Visual-Reference-Conditioned Agentic Generation through Web Development

Yuchi Wang, Rongyao Fang, Weihao Yu, Xilin Wei, Tiancheng Gu, Dingkang Yang, Hang Zhang, Dayiheng Liu, Hongsheng Li, Shuai Bai · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.26826 · cited by 0 works (OpenAlex) · open-access PDF

Hindi

एजेंसी के मूल उपकरणों के उपयोग और कोडिंग कौशल को विकसित करने के अलावा, एजेंसी उत्पादन में दृश्य संदर्भों को प्रभावी ढंग से एकीकृत करना एआई एजेंटों को वास्तविक दुनिया के उत्पादकता कार्यों के लिए लागू करने के लिए उतना ही आवश्यक है। हम वेबपेज विकास के माध्यम से इस महत्वपूर्ण क्षमता का अध्ययन करते हैं, एक व्यावहारिक और आसानी से मूल्यांकन योग्य सेटिंग जिसमें मौजूदा संदर्भ मुख्य रूप से आदर्शित रहते हैं: वे आमतौर पर दृश्य लक्ष्यों को पुनर्निर्माण करने या पाठ निर्देशों से ही वेबपेज उत्पन्न करने पर ध्यान केंद्रित करते हैं, दृश्य उदाहरणों से विकसित होने के अधिक सामान्य कार्यप्रवाह को अनदेखा करते हुए। विशेष रूप से, हम RefCraft को पेश करते हैं, 300 यथार्थवादी मल

Machine translation (Meta M2M100); the English original follows.

Abstract

Beyond basic tool use and coding skills, effectively incorporating visual references into agentic generation is equally essential for applying AI agents to real-world productivity tasks. We study this crucial capability through webpage development, a practical and readily evaluable setting in which existing benchmarks remain largely idealized: they typically focus on reconstructing visual targets or generating webpages from textual instructions alone, overlooking the more common workflow of developing from visual examples. Specifically, we introduce RefCraft, a benchmark comprising 300 realistic multimodal webpage-development tasks that combine natural-language instructions with screenshots from one to five reference webpages. Agents must selectively interpret and utilize these references while rendering, visually inspecting, and iteratively refining their outputs. We evaluate the resulting open-ended artifacts using independently verifiable keypoints and complementary programmatic and VLM judges. Across nine frontier (M)LLMs, the strongest system achieves an overall score of only 52.12 out of 100, revealing that visual-reference-conditioned agentic generation remains a substantial challenge for current models in practical webpage-development settings.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Computer science, Benchmarking, Workflow, Focus (optics), Artificial intelligence, Web application

Is this paper real? This page was built from OpenAlex and arXiv records, not generated. Software can verify any reference in one call: GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.26826, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txt

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange