# Automatically Enhancing the Quality of Android App Bug Reports

DevFeed: [Automatically Enhancing the Quality of Android App Bug Reports](<https://devfeed.tech/articles/automatically-enhancing-the-quality-of-android-app-bug-reports-113464.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2604.01148>)

Author: Antu Saha, Atish Kumar Dipongkor, Sam Bennett, Kevin Moran, Andrian Marcus, Oscar Chaparro

Published: 2026-11-03T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Software Engineering](<https://devfeed.tech/sources/arxiv-software-engineering.md>)

Topics: [Android](<https://devfeed.tech/topics/android.md>), [Ground truth / benchmark quality](<https://devfeed.tech/topics/ground-truth-benchmark-quality.md>), [Test automation](<https://devfeed.tech/topics/test-automation.md>)

Tags: [abstract](<https://devfeed.tech/tags/abstract.md>), [agent](<https://devfeed.tech/tags/agent.md>), [android](<https://devfeed.tech/tags/android.md>), [app](<https://devfeed.tech/tags/app.md>), [application](<https://devfeed.tech/tags/application.md>), [applications](<https://devfeed.tech/tags/applications.md>), [approach](<https://devfeed.tech/tags/approach.md>), [arxiv](<https://devfeed.tech/tags/arxiv.md>), [automated](<https://devfeed.tech/tags/automated.md>), [automatic](<https://devfeed.tech/tags/automatic.md>), [automatically](<https://devfeed.tech/tags/automatically.md>), [based](<https://devfeed.tech/tags/based.md>), [behavior](<https://devfeed.tech/tags/behavior.md>), [bug](<https://devfeed.tech/tags/bug.md>), [bug-reports](<https://devfeed.tech/tags/bug-reports.md>), [bugs](<https://devfeed.tech/tags/bugs.md>), [complete](<https://devfeed.tech/tags/complete.md>), [cs-se](<https://devfeed.tech/tags/cs-se.md>), [enhancing](<https://devfeed.tech/tags/enhancing.md>), [quality](<https://devfeed.tech/tags/quality.md>), [reports](<https://devfeed.tech/tags/reports.md>)

## AI overview

BUGSCRIBE enhances Android bug reports by linking users' reports with app-specific UI execution information to generate Observed Behavior, Expected Behavior, and Steps to Reproduce. The authors use a bug report quality model to select context for each component. In an evaluation of 48 reports from 26 Android apps against manually constructed ground truth, BUGSCRIBE improved Steps to Reproduce quality by 44.2%-84.7% and Observed/Expected Behavior quality by up to 35.2% over the original reports and three LLM-based baselines. Reports generated by BUGSCRIBE also raised an LLM-based agent's bug reproduction rate by 28.1%-57.7% versus those comparisons. These findings are limited to the reported evaluation; the supplied text does not describe implementation details.

## Source excerpt

arXiv:2604.01148v3 Announce Type: replace Abstract: Most defects in mobile applications are visually observable on the device screen. Since automated mechanisms for detecting and reporting such defects are often unavailable, users, testers, and developers must manually submit bug reports. However, these reports are frequently incomplete, ambiguous, or inaccurate, often lacking the information needed to understand, reproduce, and diagnose defects. We formulate automatic bug report enhancement as the problem of connecting user-written bug reports with application execution. We present BUGSCRIBE, an LLM-powered approach that links bug report information with app-specific UI execution information to infer and generate accurate, complete, and correct Observed Behavior (OB), Expected Behavior (EB), and Steps to Reproduce (S2Rs). To support BUGSCRIBE's design and evaluation, we develop a bug report quality model and use it to identify the most effective context for each component. We evaluate BUGSCRIBE on 48 bug reports from 26 Android applications with manually constructed ground truth. Our results show that BUGSCRIBE generates higher-quality bug report components than the original reports and three LLM-based baselines, improving S2R quality by 44.2%--84.7%, and OB/EB quality by up to 35.2%. We further show that BUGSCRIBE-generated reports help an LLM-based agent reproduce Android bugs, improving the reproduction rate by 28.1%--57.7% compared to the original reports and the baselines.