Newest papers

InterWebCoder: Learning Interactive Webpage Generation from Executable Tests via Reinforcement Learning

Jingyu Xiao, D. Z. Dai, Yuxuan Wan, Jen-tse Huang, Yintong Huo, Hongyu Zhang, Michael Rung-Tsong Lyu · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.28610 · cited by 0 works (OpenAlex) · open-access PDF

Portuguese

Os dados de treinamento escalável devem capturar ações do usuário, transições de estado e resultados esperados, enquanto o código da página da web do mundo real é muitas vezes entrelaçado com scripts irrelevantes e dependências externas. Além disso, a verificação baseada em agentes GUI existente fornece feedback funcional lento e potencialmente instável. Para enfrentar esses desafios, propomos o InterWebCoder, um framework eficiente para a geração de código da página da web interactiva. O InterWebCoder introduz um script guiado por especificações de teste e sintaxe de dados verificada por execução que registra trajetórias de interação do mundo real54 e sintetiza o código da página da web auto-controlado com scripts de teste executáveis. O mecanismo de reparo de custos de falha da Aurea usa a prova

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

Abstract

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 generation. InterWebCoder introduces a Test-Specification-Guided and Execution-Verified Data Synthesis pipeline that records real-world interaction trajectories and synthesizes self-contained webpage code with executable test scripts. A failureattributed repair mechanism uses runtime evidence to locate and iteratively fix errors in either the webpage code or test script. We then combine test-ID-weighted supervised fine-tuning with group-relative policy optimization, directly optimizing functional correctness and visual fidelity using test pass rates and state-level visual similarity. This replaces costly GUI-agent verification with fast, reproducible executable feedback. Our pipeline produces 1,736 verified samples from 2,058 tasks, achieving an 84.35% synthesis success rate. On IWR-Bench and Vision2Web, InterWebCoder achieves final scores of 48.54 and 48.42 with a 9B backbone, outperforming 30B-level models and Gemini-3.7-Flash while remaining competitive with Claude-Sonnet-5. It reduces reward-computation latency by over 97%, eliminates external MLLM verification costs, and accelerates end-to-end training by up to 1.4x.

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

Topics: Computer science, Executable, Web page, Correctness, Scripting language, Code (set theory)

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