Yuchi Wang, Rongyao Fang, Weihao Yu, Xilin Wei, Tiancheng Gu, Dingkang Yang, Hang Zhang, Dayiheng Liu · 2026 · arXiv
DOI: 10.48550/arXiv.2610.26826 · open-access PDF
Di luar keterampilan penggunaan alat dasar dan pengkodean, mengintegrasikan referensi visual secara efektif ke dalam generasi agentik sama pentingnya untuk menerapkan agen AI pada tugas produktivitas dunia nyata. Kami mempelajari kemampuan penting ini melalui pengembangan halaman web, pengaturan yang praktis dan mudah dievaluasi di mana referensi yang ada tetap sebagian besar diidealisasi: mereka biasanya berfokus pada membangun kembali target visual atau menghasilkan halaman web dari instruksi teks saja, mengabaikan alur kerja yang lebih umum untuk mengembangkan dari contoh visual.
Machine translation (Meta M2M100); the English original follows.
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 realist
Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese
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.txtSources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange