From Bug Reports to Browser-Executable Procedures: An LLM-Driven Agent for Web GUI Bug Reproduction

• URL: http://arxiv.org/abs/2608.03598v1
• Date: Tue, 04 Aug 2026 12:50:43 GMT
• Title: From Bug Reports to Browser-Executable Procedures: An LLM-Driven Agent for Web GUI Bug Reproduction
• Abstract summary: ReBug is a context-aware agent system that reconstructs, executes, and validates browser-level reproduction procedures from web GUI bug reports.<n>We evaluate ReBug on 667 real-world bug reports from four open-source web applications.
• Score: 1.746500363342869
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• CUADebug: Diagnosing and Repairing Computer-Use Agent Failures [65.56066380320107]
  Computer-use agents (CUAs) operate real desktop and web interfaces through screenshots, mouse and keyboard actions, and stateful UI feedback.<n>Unlike text-only agents, CUA failures arise from coupled visual perception, grounding, low-level interaction, task reasoning, and environment dynamics.<n>We introduce CUA Debug, a framework for diagnosing and repairing CUA failures.
  arXiv  Detail & Related papers  (2026-07-31T13:59:45Z)
• AgentDebugX: An Open-Source Toolkit for Failure Observability, Attribution, and Recovery in LLM Agents [83.37969790806069]
  LLM agent failures are difficult to debug because the step where an error surfaces is often not the one that caused it.<n>We present Agent DebuggerX, an open-source framework that organizes debug as a closed loop of Detect, Attribute, Recover, and Rerun.<n>At its core, Deep Debugger performs multi-turn root-cause diagnosis through global trajectory understanding.
  arXiv  Detail & Related papers  (2026-07-21T06:21:13Z)
• ReProAgent: Tool-Augmented Multi-Stage Agentic Generation of Bug Reproduction Tests from Issue Reports [27.433981940933688]
  ReProAgent is a framework for reproduction test generation from issue reports.<n>It decomposes the task into four agent stages: bug localization, root cause analysis, test planning, and test generation.<n>Experiments on SWT-bench-lite and SWT-bench-verified show that ReProAgent successfully reproduces 58.43% and 70.30% of issues.
  arXiv  Detail & Related papers  (2026-07-10T06:25:18Z)
• ReproRepo: Scaling Reproducibility Audits with GitHub Repository Issues [54.98461672730087]
  We introduce ReproRepo, a scalable framework for evaluation that leverages human-raised GitHub issues as naturally occurring supervision on realistic reproduction blockers.<n>We instantiate ReproRepo on 1,149 recent machine learning papers from major conferences and evaluate four frontier model-agent configurations.<n>Our results show that LLM agents, even without executing code, can identify many real-world problems from paper-repository pairs.
  arXiv  Detail & Related papers  (2026-06-16T17:58:05Z)
• GTA: Generating Long-Horizon Tasks for Web Agents at Scale [82.43869456830664]
  We introduce a scalable framework, GTA, that integrates crawling, retrieval-based seeding, in-context generation, and automated quality control.<n>We instantiate the pipeline on over 50 websites covering e-commerce, government, forums, and news, with multilingual and multi-hop coverage.<n>Our contributions are three-fold: (i) formalizing multi-hop web-agent task generation, (ii) proposing an efficient and validated pipeline for automatic data creation, and (iii) releasing a dynamic benchmark with reproducible evaluation.
  arXiv  Detail & Related papers  (2026-05-28T01:05:50Z)
• ClawMark: A Living-World Benchmark for Multi-Turn, Multi-Day, Multimodal Coworker Agents [77.22389710754452]
  We introduce bench, a benchmark for coworker agents built around multi-turn multi-day tasks.<n>The current release contains 100 tasks across 13 professional scenarios, executed against five stateful sandboxed services.<n>The strongest model reaches 75.8 weighted score, but the best strict Task Success is only 20.0%, indicating that partial progress is common.
  arXiv  Detail & Related papers  (2026-04-26T16:05:02Z)
• ViBR: Automated Bug Replay from Video-based Reports using Vision-Language Models [17.094299668194378]
  ViBR is a lightweight and fully automated approach that reproduces bugs directly from GUI recordings.<n>Results show that ViBR successfully reproduces 72% of bug recordings, significantly outperforming state-of-the-art baselines and ablation variants.
  arXiv  Detail & Related papers  (2026-04-21T18:28:02Z)
• WebGen-Agent: Enhancing Interactive Website Generation with Multi-Level Feedback and Step-Level Reinforcement Learning [51.14454312533818]
  WebGen-Agent is a novel website-generation agent that leverages comprehensive and multi-level visual feedback.<n>We introduce textitStep-GRPO with Screenshot and GUI-agent Feedback to improve the ability of LLMs to act as the reasoning engine of WebGen-Agent.<n>WebGen-Agent increases the accuracy of Claude-3.5-Sonnet from 26.4% to 51.9% and its appearance score from 3.0 to 3.9, outperforming the previous state-of-the-art agent system.
  arXiv  Detail & Related papers  (2025-09-26T17:59:51Z)
• BugRepro: Enhancing Android Bug Reproduction with Domain-Specific Knowledge Integration [4.833035081314386]
  BugRepro is a novel technique that integrates domain-specific knowledge to enhance the accuracy and efficiency of bug reproduction.<n>BugRepro significantly outperforms two state-of-the-art methods.
  arXiv  Detail & Related papers  (2025-05-20T15:48:34Z)
• Semantic GUI Scene Learning and Video Alignment for Detecting Duplicate Video-based Bug Reports [16.45808969240553]
  Video-based bug reports are increasingly being used to document bugs for programs centered around a graphical user interface (GUI) We introduce a new approach, called JANUS, that adapts the scene-learning capabilities of vision transformers to capture subtle visual and textual patterns that manifest on app UI screens. Janus also makes use of a video alignment technique capable of adaptive weighting of video frames to account for typical bug manifestation patterns.
  arXiv  Detail & Related papers  (2024-07-11T15:48:36Z)
• Prompting Is All You Need: Automated Android Bug Replay with Large Language Models [28.69675481931385]
  We propose AdbGPT, a new lightweight approach to automatically reproduce the bugs from bug reports through prompt engineering. AdbGPT leverages few-shot learning and chain-of-thought reasoning to elicit human knowledge and logical reasoning from LLMs. Our evaluations demonstrate the effectiveness and efficiency of our AdbGPT to reproduce 81.3% of bug reports in 253.6 seconds.
  arXiv  Detail & Related papers  (2023-06-03T03:03:52Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.