Newest papers

Step-Aligned Script Generation with Verification and Recovery for Web Automation Testing

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

Korean

최신 LLM 기반 웹 에이전트는 실시간 브라우저 세션에서 천연 언어 작업을 완료 할 수 있지만, 작업 완료는 실행 가능한 코드, 목표 상태 주장 및 단계 수준의 출처가 생성 된 코드의 각 단계를 생성, 선택 증거, 실행 결과 및 복구 역사에 연결하는 실행 가능한 코드, 다시 재생할 수있는 코드를 생성하는 것과 동일하지 않습니다. 우리는 TESSARA를 제시합니다. TESSARA는 자연 언어 시험 의도에 자연 언어 생성 프레임 워크를 변환하는 자연 언어 시험 의도는 실행 가능한 스크립트, 목표 상태 주장 및 단계 수준의 출처로 구성된 Playwright 스크립트로 변환합니다.

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

Abstract

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

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