Date of Defense

31-3-2026 3:00 PM

Location

E1-1041

Document Type

Thesis Defense

Degree Name

Master of Science in Software Engineering

College

College of Information Technology

Department

Computer Science and Software Engineering

First Advisor

Yasir Mahmood

Keywords

Coding Agent, Pull Requests, Large Language Models (LLM), Human-Computer Interaction (HCI), Prompt Engineering, Software Engineering

Abstract

This thesis investigates the real-world behavior of LLM-driven coding agents that generate code changes and submit pull requests (PRs) to public software repositories. As these tools evolve from autocomplete-style assistants into more autonomous agents, their contributions increasingly interact with socio-technical review processes (human reviewers, bots, CI/CD gates, and project norms). This thesis focuses on understanding why agent-generated PRs are accepted or rejected and what these outcomes reveal about current agent limitations in practical development workflows. The main objective of this thesis is to systematically characterize rejection patterns and failure modes of agent-generated pull requests in real repositories. Specifically, the thesis aims to quantify acceptance vs. rejection trends across agents and time, derive a structured taxonomy of rejection reasons grounded in reviewer comments and repository signals, and translate the empirical findings into actionable recommendations for practitioners and for designers of more reliable, reflexive coding agents. The research employs an empirical software engineering methodology combining large-scale data mining, quantitative analysis, and qualitative labeling.

Share

COinS
 
Mar 31st, 3:00 PM

Software Engineering in the Age of Coding Agents: Failure Modes and Rejection Patterns

E1-1041

This thesis investigates the real-world behavior of LLM-driven coding agents that generate code changes and submit pull requests (PRs) to public software repositories. As these tools evolve from autocomplete-style assistants into more autonomous agents, their contributions increasingly interact with socio-technical review processes (human reviewers, bots, CI/CD gates, and project norms). This thesis focuses on understanding why agent-generated PRs are accepted or rejected and what these outcomes reveal about current agent limitations in practical development workflows. The main objective of this thesis is to systematically characterize rejection patterns and failure modes of agent-generated pull requests in real repositories. Specifically, the thesis aims to quantify acceptance vs. rejection trends across agents and time, derive a structured taxonomy of rejection reasons grounded in reviewer comments and repository signals, and translate the empirical findings into actionable recommendations for practitioners and for designers of more reliable, reflexive coding agents. The research employs an empirical software engineering methodology combining large-scale data mining, quantitative analysis, and qualitative labeling.