Jingyu Xiao, Dasen Dai, Yuxuan Wan, Jen-tse Huang, Yintong Huo, Hongyu Zhang, Michael R. Lyu · 2026 · arXiv
DOI: 10.48550/arXiv.2610.28610 · open-access PDF
Halaman web interaktif mendasari aplikasi modern, tetapi mereproduksi tampilan visual mereka dan perilaku multi-langkah tetap menantang untuk model bahasa besar multimodal (MLLM). Data pelatihan yang dapat diperluas harus menangkap tindakan pengguna, transisi negara, dan hasil yang diharapkan, sementara kode halaman web dunia nyata sering bingung dengan script yang tidak relevan dan ketergantungan eksternal. Selain itu, verifikasi berbasis GUI yang ada memberikan umpan balik fungsional yang lambat dan berpotensi tidak stabil.
Machine translation (Meta M2M100); the English original follows.
Interactive webpages underpin modern applications, but reproducing both their visual appearance and multi-step behavior remains challenging for multimodal large language models (MLLMs). Scalable training data must capture user actions, state transitions, and expected outcomes, while real-world webpage code is often entangled with irrelevant scripts and external dependencies. Moreover, existing GUI-agent-based verification provides slow and potentially unstable functional feedback. To address these challenges, we propose InterWebCoder, an efficient framework for interactive webpage code generat
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=2610.28610, 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