Towards AI-Powered Localization of Software Bugs: From Semantic Understanding to Agentic Cognition

Abstract

Software bugs cost billions annually and consume nearly 50% of developers' time. Despite decades of research, automated bug localization remains challenging according to software practitioners. Traditional approaches (e.g., Information Retrieval) rely on surface-level textual matching, while deep learning methods require extensive training data, limiting their effectiveness and applicability. Recent Large Language Models (LLMs) offer unprecedented capabilities in understanding both natural language and source code, yet their potential for bug localization remains underexplored. In this dissertation work, we hypothesize that through program semantics understanding, contextual reasoning, and developer-inspired debugging practices, bug localization systems can better overcome the limitations of existing approaches. We ask three research questions targeting the hypothesis, conduct three studies leveraging different forms of intelligence, and use them to test our hypothesis. Our studies suggest that bug localization can be improved significantly by (1) leveraging program semantics to bridge gaps between bug report and source code, (2) capturing Intelligent Relevance Feedback through contextual reasoning, and (3) replicating developers' cognitive debugging practices.