CSCI 7000-11 Fall 2025: GenAI-powered Software Engineering

TIME AND LOCATION

Tue and Thu, 2:00-3:15 PM

Meets Remotely on Zoom: https://cuboulder.zoom.us/j/98033152097 (you need to authenticate with your colorado.edu credentials)

Three times per semester (first day of class on Aug 21, mid semester, and last week on Dec 2 or 4), this class meets in person: Discovery Learning Center (DLC) 1B70

INSTRUCTOR

Prof. Danny Dig (danny.dig@colorado.edu)
Office: On Zoom
Phone: (303) 492-1293
Office Hours: right after class, additional slots offered each week to accomodate various schedules.

Prerequisites

Students should have basic knowledge of Computer Science undergrad classes, including software engineering, programming languages, systems, ML/AI as demonstrated by undergrad courses at CU. This is NOT an introductory grad course to Software Engineering, for those students we recommend other grad courses such as Foundations of Software Engineering (CSCI 5828). This course assumes you are a competent software engineer already -- we are looking into how you can augment your current skills to include GenAI supported software development. If you are not sure whether you can attend this course, please consult the instructor (email: danny.dig@colorado.edu)

ABOUT THE COURSE

The purpose of this research course is to expose students to seminal topics and recent trends in the field of GenAI for Software Engineering.

Software development is undergoing a profound transformation as GenAI becomes increasingly integrated into development practices. This brand new course ensures that our students are not only aware of these developments but are also prepared to lead in this new era. In this class, students (i) understand the capabilities and limitations of GenAI systems deployed in production or in research; (ii) Learn to critically assess AI-assisted development workflows; (iii) Gain hands-on experience using GenAI in tasks such as testing, debugging, code synthesis, and refactoring.

In this highly interactive, Seminar-style class featuring Instructor-guided exploration and student-led discussions, we will be investigating (i) innovative use of GenAI in software engineering processes and tasks (compelling applications) and (ii) the research technical thrusts that enable the exciting applications of the future. Our exploration will consist of in-class discussions of the cutting-edge research literature, interactions with industry thought leaders, and team projects that encourage risk taking.

The course will offer an opportunity for students to pursue research-oriented or novel industrial term projects in small teams (3-4 students). Students may pursue any project of their choosing that explores the intersection of GenAI with processes and tools used in Software Engineering.

The course will offer several opportunities to learn from the movers and shakers in GenAI from industry and academic research labs.

COURSE OBJECTIVES

expand student's knowledge more broadly about GenAI-based Software Engineering research & practice through reading research papers and industry surveys
develop critical thinking abilities by being able to assess the quality of published research and pose new research questions
practice giving scientific presentations and teaching others
engage in active learning activities in class, such as student-guided discussions on research and applications for GenAI in Software Engineering
practice developing a research or novel-industrial software development project through all its stages: formulating a research problem, posing research questions, gathering related work, designing a solution, evaluating the solution empirically, writing a research paper
practice engaging in dialogue with thought leaders in GenAI Software Engineering.
have fun learning

View the full Course Syllabus page for grading, policies, etc.

SCHEDULE

This is a tentative schedule to give you an idea of the topics that we study in the class. Some of the assigned papers are likely to change based on the projects that students work on, once we finalize the list of course projects.

Date	Presenter	Readings
08/21	Danny Dig	Course Introduction and discussing your expectations. Slides presented in class. Read this excellent resource on how to Read an Engineering Research paper (by William Griswold). Sign up on Piazza.
08/26	Danny Dig	Slides presented in class Read two papers: (1) Large Language Models for Software Engineering: A Systematic Literature Review by Hou et al., TOSEM 2024 Read: (2) Large Language Models for Software Engineering: Survey and Open Problems by Fan et al., ICSE 2023: Future of Software Engineering. Afterwards, write a paper critique for each paper. After you write the paper critique, please submit it here on Canvas (due by Mon, Aug 25 at 5pm). Read course syllabus (and other info on our class webpage).
08/28	Danny Dig	Slides presented in class Part 2 - Large Language Models for Software Engineering: A Systematic Literature Review by Hou et al., TOSEM 2024 Large Language Models for Software Engineering: Survey and Open Problems by Fan et al., ICSE 2023: Future of Software Engineering. Read about the research project (and other info on our class webpage).
09/02	Danny Dig	Slides presented in class Unprecedented Code Change Automation: The Fusion of LLMs and Transformation by Example by Dilhara et al., FSE'24 Next-Generation Refactoring: Combining LLM Insights and IDE Capabilities for Extract Method by Pomian et al., ICSME'24.
09/04	Danny Dig	Slides presented in class Together We Are Better: LLM, IDE and Semantic Embedding to Assist Move Method Refactoring by Bellur et al., ICSME'25
09/09	David Lo	Notice that this class starts at 3pm MT Code, Critique, Cure: Advancing LLM Reasoning for AI-Augmented Software Maintenance By David Lo -- keynote at ICSME'25.
09/11	All Students	Pitch Project Idea
09/16	Students	Project Bazaar Form project teams Notice this class meets in person: Discovery Learning Center (DLC) 1B20
09/18	Students	Project Bazaar Form project teams Notice this class meets in person: Discovery Learning Center (DLC) 1B20
09/23	Blake, Ishika	Migrating Code At Scale With LLMs At Google by Ziftci et al., in FSE'25 TestSpark: IntelliJ IDEA's Ultimate Test Generation Companion by Sapozhnikov et al., in ICSE'24
09/25	Everyone	Milestone 1
09/30	Martini, Evan	A Taxonomy of Inefficiencies in LLM-Generated Code. By Abbassi et al., ICSME'25. Can LLMs Update API Documentation? By Lee et al., ICSME'25.
10/02	Jarek, Varun	AutoCodeRover: Autonomous program improvement by Zhang et al., in ISSTA'24 RepairAgent: An Autonomous, LLM-Based Agent for Program Repair by Bouzenia et al., ICSE'25
10/07	Uditanshu, Archit	Using AI-Based Coding Assistants in Practice: State of Affairs, Perceptions, and Ways Forward by Sergeyuk et al., ICSME'25 journal-first paper. The Impact of Fine-tuning Large Language Models on Automated Program Repair by Machacek et al., ICSME'25.
10/09	No Class	CU Boulder Reading Day.
10/14	Raihan, Vijay	Why AI Agents Still Need You: Findings from Developer-Agent Collaborations in the Wild by Kumar et al., to Appear in ASE'25. An Empirical Study on the Potential of LLMs in Automated Software Refactoring by Liu et al, Journal of Automated Software Engineering, 2025.
10/16	Everyone	Milestone 2
10/21	Blake, Jarek	RefactoringMiner 2.0 by Tsantallis et al, IEEE Transactions of Software Engineering. An LLM-based multi-agent framework for agile effort estimation by Bui et al., to Appear in ASE'25.
10/23	Martini, Evan	MANTRA: Enhancing Automated Method-Level Refactoring with Contextual RAG and Multi-Agent LLM Collaboration by Xu et al., 2025 Backdoors in Code Summarizers: How Bad Is It? by Wang et al., to Appear in ASE'25.
10/28	Ishika, Varun	Prompting Matters: Assessing the Effect of Prompting Techniques on LLM-Generated Class Code by Yuen et al. in ICSME'25 NIER track. NIODebugger: A Novel Approach to Repair Non-Idempotent-Outcome Tests with LLM-Based Agent by Ke et al., in ICSE'25.
10/30	Uditanshu, Archit	One-to-One or One-to-Many? Suggesting Extract Class Refactoring Opportunities with Intra-class Dependency Hypergraph Neural Network" by Cui et al, in ISSTA'24. Hierarchical Knowledge Injection for Improving LLM-based Program Repair by Ehsani et al., to appear in ASE'25.
11/04	Raihan, Vijay	TBA TBA
11/06	Everyone	Milestone 3
11/11	Giuseppe "Beppe" Raffa	Principal AI Engineer and Research Manager at Intel Labs, presents exciting applications they've been developing based on GenAI.
11/20	Haifeng Chen	The Head of Data Science at NEC Laboratories America presents exciting research in the field of GenAI.
11/25		No class -- Fall Break
11/27		No class -- Fall Break
12/02	Everyone	Milestone 4
12/07	No final exam.	Submit final project