From Bug Reports to Browser-Executable Procedures: An LLM-Driven Agent for Web GUI Bug Reproduction
- ID: 39c6f5cd
- Original URL: https://arxiv.org/abs/2608.03598
- PDF: https://arxiv.org/pdf/2608.03598v1
- Author(s): Cunming Zhang, Yu Pei, Michail Papadakis
- Date: 2026-08-04
- Category: coding
- Source type: paper
- Tags: bug-reproduction, browser-agent, web-gui, software-testing, llm-agents
- Quality score: 4/5
- Fetched at: 2026-08-06T15:43:42+00:00
- Obsidian evidence: OpenClaw定时任务/论文流水线/2026-08-06-论文流水线.md
中文导读
ReBug 把自然语言 Web GUI bug report 转成浏览器可执行复现流程。系统分为 preparation 与 execution 两段：先从报告和工件补齐依赖、输入文件等前置条件并生成高层计划，再驱动真实浏览器交互，维护页面状态与 action history，并根据报告期望验证最终状态。作者在四个开源 Web 应用的 667 个真实 bug reports 上评测，报告平均 RSR 49.96%、任务完成率 74.96%、动作执行成功率 86.54%。
为什么值得关注
连接软件维护、浏览器自动化和 agent 真实环境执行验证。
English Summary
Reproducing web GUI bugs from natural-language bug reports is critical for software maintenance, but remains difficult because reports often lack prerequisites such as dependencies and input files. Existing bug reproduction techniques mainly target code units or mobile applications and lack end-to-end visual execution and validation for web GUIs. We present ReBug, a context-aware agent system that reconstructs, executes, and validates browser-level reproduction procedures from web GUI bug reports by driving a real browser. ReBug separates reproduction into two stages. In the preparation stage, ReBug reconstructs missing prerequisites from the report and available artifacts, and it produces a high-level reproduction plan. In the execution stage, it performs tool-mediated interactions in the browser, maintains structured summaries of page state and action history, and validates the final state against expectations derived from the report. We evaluate ReBug on 667 real-world bug reports from four open-source web applications. On controlled current deployments, ReBug outperforms both baselines, achieving an average RSR of 49.96%, a mean task completion rate of 74.96%, and a mean action execution success rate of 86.54%. Our results show that explicit context reconstruction and state-aware browser execution effectively support report-derived browser reproduction, while historical replay shows that successful procedures often expose the original bug-present behavior on restored buggy versions.
原文摘要 / Source Excerpt
From Bug Reports to Browser-Executable Procedures: An LLM-Driven Agent for Web GUI Bug Reproduction
- arXiv: https://arxiv.org/abs/2608.03598
- PDF: https://arxiv.org/pdf/2608.03598v1
- Authors: Cunming Zhang, Yu Pei, Michail Papadakis
- Published: 2026-08-04
- Updated: 2026-08-04
- Categories: cs.SE
Abstract
Reproducing web GUI bugs from natural-language bug reports is critical for software maintenance, but remains difficult because reports often lack prerequisites such as dependencies and input files. Existing bug reproduction techniques mainly target code units or mobile applications and lack end-to-end visual execution and validation for web GUIs. We present ReBug, a context-aware agent system that reconstructs, executes, and validates browser-level reproduction procedures from web GUI bug reports by driving a real browser. ReBug separates reproduction into two stages. In the preparation stage, ReBug reconstructs missing prerequisites from the report and available artifacts, and it produces a high-level reproduction plan. In the execution stage, it performs tool-mediated interactions in the browser, maintains structured summaries of page state and action history, and validates the final state against expectations derived from the report. We evaluate ReBug on 667 real-world bug reports from four open-source web applications. On controlled current deployments, ReBug outperforms both baselines, achieving an average RSR of 49.96%, a mean task completion rate of 74.96%, and a mean action execution success rate of 86.54%. Our results show that explicit context reconstruction and state-aware browser execution effectively support report-derived browser reproduction, while historical replay shows that successful procedures often expose the original bug-present behavior on restored buggy versions.