Studying and Automating Issue Resolution for Software Quality

TL;DR

The paper tackles challenges in software issue resolution posed by incomplete reports, opaque workflows, and cognitively demanding tasks. It proposes three directions: enhance issue report quality with LLMs and app-context, empirically study traditional versus AI-augmented workflows, and automate tasks such as Buggy UI Localization and Solution Identification using ML/DL/LLMs. Notable contributions include the AstroBR framework for S2R quality, an empirical Mozilla Firefox workflow study revealing non-linear patterns, and positive automation results (52% top-3 screen localization, 60% top-3 component localization, 9-12% Hits@10 gains; Llama-3_ft F1 0.716 and ensemble 0.737). These results offer empirical guidance and open-source tools toward AI-driven, reliable issue resolution to sustain software quality.

Abstract

Effective issue resolution is crucial for maintaining software quality. Yet developers frequently encounter challenges such as low-quality issue reports, limited understanding of real-world workflows, and a lack of automated support. This research aims to address these challenges through three complementary directions. First, we enhance issue report quality by proposing techniques that leverage LLM reasoning and application-specific information. Second, we empirically characterize developer workflows in both traditional and AI-augmented systems. Third, we automate cognitively demanding resolution tasks, including buggy UI localization and solution identification, through ML, DL, and LLM-based approaches. Together, our work delivers empirical insights, practical tools, and automated methods to advance AI-driven issue resolution, supporting more maintainable and high-quality software systems.