Hridya Dhulipala, Xiaokai Rong, Aashish Yadavally, Tien N. Nguyen · 2026 · arXiv (Cornell University)
DOI: 10.48550/arxiv.2610.25601 · cited by 0 works (OpenAlex) · open-access PDF
La génération automatisée de tests web efficaces de bout en bout reste coûteuse: les développeurs doivent identifier des sélecteurs stables, coder des flux de travail en plusieurs étapes, joindre des affirmations et maintenir des scripts à mesure que les interfaces évoluent. Les agents Web récents basés sur LLM peuvent compléter des tâches en langue naturelle dans une session de navigateur en direct, mais la réalisation des tâches n'est pas la même que la production d'un artifice de testware consistant en un code d'interaction exécutable, des affirmations d'état de but et de provenance à partir d'un état de réinitialisation, inspectables par les développeurs et liés à un oracle. Nous présentons TESSARA, un cadre de génération de script de test
Machine translation (Meta M2M100); the English original follows.
Automated generation of end-to-end web tests remains costly: developers must identify stable selectors, encode multi-step workflows, attach assertions, and maintain scripts as interfaces evolve. Recent LLM-based web agents can complete natural-language tasks in a live browser session, but task completion is not the same as producing a test-ware artifact - code that is executable, replay-able from a reset state, inspectable by developers, and tied to an oracle. We present TESSARA, an adaptive test-script generation framework that converts natural-language test intent into Playwright scripts consisting of executable interaction code, goal-state assertions, and step-level provenance linking each step to its generated code fragment, selector evidence, execution outcome, and repair history. TESSARA grounds each planned step via Step-Aligned Scripting (SAS), enabling fine-grained failure localization, selective regeneration of failing suffixes, and reversibility-aware backtracking that avoids undoing likely commit points (e.g., form submissions). A three-level verification pipeline (syntactic, execution, and semantic/oracle), detects and repairs malformed code, interaction failures, and incorrect landing states. We evaluate TESSARA on three public web benchmarks, measuring script executability, oracle satisfaction, replay stability, and repair efficiency, and show substantial improvements over baselines and underlying VLMs used directly as script generators.
Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese
Topics: Computer science, Scripting language, Commit, Executable, Web application, Programming language
GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.25601, 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