This study presents a comprehensive survey and comparative analysis of AI-based techniques for error detection and automated program repair, revealing that while LLM-based approaches significantly outperform traditional methods in repair capability, challenges remain in patch correctness validation, computational cost, and generalization to real-world codebases.
HELP, a program optimizer that prompts an LLM to generate diverse, non-overlapping atomic edits and then systematically selects and composes them into coherent program improvements using evaluator scores, is introduced.
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.
Current research is summarized to identify key gaps and future directions to optimize LLM based APR are proposed, to assure its reliability and scalability in real world software development.
Test4Py is presented, a novel framework that enhances type correctness in automated test generation for Python by leveraging the program’s call graph to capture richer contextual information about parameters, and introducing a behavior-based type inference mechanism that accurately infers parameter types and constructs valid test inputs.
A dataset of LLM-generated broken-to-fixed test pairs is built, where initially failing tests are repaired via a loop under zero-shot, few-shot, and chain-of-thought prompting, and the performance of prompting strategies through repair rate and post-repair coverage is compared.
