# Combining Language and App UI Analysis for the Automated Assessment of Bug Reproduction Steps

arXiv: https://arxiv.org/abs/2502.04251 · HTML: https://mlsanity.com/paper/2502.04251/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 57 references that are in the map.
- First posted on arXiv 6 Feb 2025.

## Builds on (most cited first, 19 of 19)

- [An Introduction to Convolutional Neural Networks](https://mlsanity.com/paper/1511.08458/) (2015)
- [Large Language Models for Software Engineering: A Systematic Literature Review](https://mlsanity.com/paper/2308.10620/) (2023)
- [Prompting Is All You Need: Automated Android Bug Replay with Large Language Models](https://mlsanity.com/paper/2306.01987/) (2023)
- [Assessing the Quality of the Steps to Reproduce in Bug Reports](https://mlsanity.com/paper/1906.07107/) (2019)
- [Translating Video Recordings of Mobile App Usages into Replayable Scenarios](https://mlsanity.com/paper/2005.09057/) (2020)
- [Auto-completing Bug Reports for Android Applications](https://mlsanity.com/paper/1705.04016/) (2017)
- [Feedback-Driven Automated Whole Bug Report Reproduction for Android Apps](https://mlsanity.com/paper/2407.05165/) (2024)
- [BURT: A Chatbot for Interactive Bug Reporting](https://mlsanity.com/paper/2302.06050/) (2023)
- [On Using GUI Interaction Data to Improve Text Retrieval-based Bug Localization](https://mlsanity.com/paper/2310.08083/) (2023)
- [Toward Interactive Bug Reporting for (Android App) End-Users](https://mlsanity.com/paper/2209.10062/) (2022)
- [An Empirical Investigation into the Reproduction of Bug Reports for Android Apps](https://mlsanity.com/paper/2301.01235/) (2023)
- [Automatically Discovering, Reporting and Reproducing Android Application Crashes](https://mlsanity.com/paper/1706.01130/) (2017)
- [V2S: A Tool for Translating Video Recordings of Mobile App Usages into Replayable Scenarios](https://mlsanity.com/paper/2103.04531/) (2021)
- [Translating Video Recordings of Complex Mobile App UI Gestures into Replayable Scenarios](https://mlsanity.com/paper/2301.01191/) (2023)
- [CrashScope: A Practical Tool for Automated Testing of Android Applications](https://mlsanity.com/paper/1801.06428/) (2018)
- [AndroR2: A Dataset of Manually Reproduced Bug Reports for Android Applications](https://mlsanity.com/paper/2106.08403/) (2021)
- [Enhancing Mobile App Bug Reporting via Real-time Understanding of Reproduction Steps](https://mlsanity.com/paper/2203.12093/) (2022)
- [Semantic GUI Scene Learning and Video Alignment for Detecting Duplicate Video-based Bug Reports](https://mlsanity.com/paper/2407.08610/) (2024)
- [Toward the Automated Localization of Buggy Mobile App UIs from Bug Descriptions](https://mlsanity.com/paper/2408.04075/) (2024)

## Built on by (most cited first, 2 of 2)

- [Past, Present, and Future of Bug Tracking in the Generative AI Era](https://mlsanity.com/paper/2510.08005/) (2025)
- [Writing Bug Reports for Software Repair Agents: What Information Matters Most?](https://mlsanity.com/paper/2607.09553/) (2026)

## Abstract (arXiv)

Bug reports are essential for developers to confirm software problems, investigate their causes, and validate fixes. Unfortunately, reports often miss important information or are written unclearly, which can cause delays, increased issue resolution effort, or even the inability to solve issues. One of the most common components of reports that are problematic is the steps to reproduce the bug(s) (S2Rs), which are essential to replicate the described program failures and reason about fixes. Given the proclivity for deficiencies in reported S2Rs, prior work has proposed techniques that assist reporters in writing or assessing the quality of S2Rs. However, automated understanding of S2Rs is challenging, and requires linking nuanced natural language phrases with specific, semantically related program information. Prior techniques often struggle to form such language to program connections - due to issues in language variability and limitations of information gleaned from program analyses. To more effectively tackle the problem of S2R quality annotation, we propose a new technique called AstroBR, which leverages the language understanding capabilities of LLMs to identify and extract the S2Rs from bug reports and map them to GUI interactions in a program state model derived via dynamic analysis. We compared AstroBR to a related state-of-the-art approach and we found that AstroBR annotates S2Rs 25.2% better (in terms of F1 score) than the baseline. Additionally, AstroBR suggests more accurate missing S2Rs than the baseline (by 71.4% in terms of F1 score).