14:00 - 15:30

Poster

Session 2 - Posters

MSR Program


Talk

When AI Agents Touch CI/CD Configurations: Frequency and Success

Mining Challenge

Pre-print

Talk

Fingerprinting AI Coding Agents on GitHub

Mining Challenge

Pre-print

Talk

When AI Code Doesn’t Stick: An Empirical Study on Reverted Changes Introduced by AI Coding Agents

Mining Challenge

File Attached

Talk

Characterizing Self-Admitted Technical Debt Generated by AI Coding Agents

Mining Challenge

File Attached

Talk

How Do Agents Perform Code Optimization? An Empirical Study

Mining Challenge

Pre-print

Talk

Comparing AI Coding Agents: A Task-Stratified Analysis of Pull Request Acceptance

Mining Challenge

Talk

More Code, Less Reuse: Investigation on Code Quality and Reviewer Sentiment towards AI-generated Pull Requests

Mining Challenge

DOI Pre-print

Talk

On the Adoption of AI Coding Agents in Open-source Android and iOS Development

Mining Challenge

Pre-print

Talk

Who Writes the Docs in SE 3.0? Agent vs. Human Documentation Pull Requests

Mining Challenge

DOI Pre-print

Talk

Testing with AI Agents: An Empirical Study of Test Generation Frequency, Quality, and Coverage

Mining Challenge

Talk

Safer Builders, Risky Maintainers: A Comparative Study of Breaking Changes in Human vs Agentic PRs

Mining Challenge

DOI Pre-print File Attached

Talk

On the Reliability of Agentic AI in Continuous Integration Pipelines

Mining Challenge

Pre-print File Attached

Talk

Early-Stage Prediction of Review Effort in AI-Generated Pull Requests

Mining Challenge

Pre-print File Attached

Talk

Test Coverage of Code Changes in AI-Generated Pull Requests

Mining Challenge

Talk

When AI Teammates Meet Code Review: Collaboration Signals Shaping the Integration of Agent-Authored Pull Requests

Mining Challenge

Pre-print

Talk

Toward Instructions-as-Code: Understanding the Impact of Instruction Files on Agentic Pull Requests

Mining Challenge

Talk

An Empirical Study of Code Clone Genealogies in Human–AI Collaborative Development

Mining Challenge

Talk

On the Footprints of Reviewer Bots' Feedback on Agentic Pull Requests in OSS GitHub Repositories

Mining Challenge

Talk

When Bots Get the Boot: Understanding Pull Request Rejections in the Era of AI Coders

Mining Challenge

Talk

Understanding the Rejection of Fixes Generated by Agentic Pull Requests - Insights from the AIDev Dataset

Mining Challenge

Talk

What to Cut? Predicting Unnecessary Methods in Agentic Code Generation

Mining Challenge

Talk

How AI Coding Agents Modify Code: A Large-Scale Study of GitHub Pull Requests

Mining Challenge

DOI Pre-print

Talk

Reliability of AI Bots Footprints in GitHub Actions CI/CD Workflows

Mining Challenge

Talk

The Dose Makes the Agent: Therapeutic Index Analysis of AI Coding Contributions

Mining Challenge

Talk

Beyond Bug Fixes: An Empirical Investigation of Post-Merge Code Quality Issues in Agent-Generated Pull Requests

Mining Challenge

Talk

Why Are Agentic Pull Requests Merged or Rejected? An Empirical Study

Mining Challenge

Sien Reeve O. Peralta Waseda University

,

Fumika Hoshi Waseda University

,

Hironori Washizaki Waseda University

,

Naoyasu Ubayashi Waseda University

,

Inase Kondo Osaka University

,

Yoshiki Higo Osaka University

,

Hiroki Mukai Ritsumeikan University

,

Norihiro Yoshida Ritsumeikan University

,

Kazuki Kusama

,

Hidetake Tanaka Nara Institute of Science and Technology

,

Youmei Fan Nara Institute of Science and Technology

Talk

Let's Make Every Pull Request Meaningful: An Empirical Analysis of Developer and Agentic Pull Requests

Mining Challenge

DOI Pre-print

Talk

Humans Integrate, Agents Fix: How Agent-Authored Pull Requests Are Referenced in Practice

Mining Challenge

Short-paper

How Do Agentic AI Systems Deal With Software Energy Concerns? A Pull Request-Based Study

Mining Challenge

Pre-print

Talk

When AI Writes Code: Investigating Security Issues in Agentic Software Changes

Mining Challenge

Talk

Novice Developers Produce Larger Review Overhead for Project Maintainers while Vibe Coding

Mining Challenge

Pre-print

Talk

Code Change Characteristics and Description Alignment: A Comparative Study of Agentic versus Human Pull Requests

Mining Challenge

Pre-print

Talk

A Task-Level Evaluation of AI Agents in Open-Source Projects

Mining Challenge

Pre-print

Talk

Behind Agentic Pull Requests: An Empirical Study on Developer Interventions in AI Agent-Authored Pull Requests

Mining Challenge

Syrine Khelifi École de technologie supérieure (ÉTS) Montréal

,

Ali Ouni Ecole de Technologie Superieure (ETS)

,

Maha Khemaja ISSAT Sousse, PRINCE Lab, University of Sousse

Talk

Readability of AI-Generated Pull Request Descriptions Across Pull Request Types

Mining Challenge

Media Attached File Attached

Short-paper

The Quiet Contributions: Insights into AI-Generated Silent Pull Requests

Mining Challenge

Pre-print

Talk

AI IDEs or Autonomous Agents? Measuring the Impact of Coding Agents on Software Development

Mining Challenge

Pre-print Media Attached

Talk

AI builds, We Analyze: An Empirical Study of AI-Generated Build Code Quality

Mining Challenge

Talk

Understanding Dominant Themes in Reviewing Agentic AI-authored Code

Mining Challenge

Pre-print

Talk

Why and When Agentic Pull Requests are (not) Accepted: An Exploratory Study

Mining Challenge

DOI Pre-print

Talk

Analyzing Message-Code Inconsistency in AI Coding Agent-Authored Pull Requests

Mining Challenge

Talk

How Do Agentic AI Systems Address Performance Optimizations? A BERTopic-Based Analysis of Pull Requests

Mining Challenge

Pre-print

Talk

Mining Type Constructs Using Patterns in AI-Generated Code

Mining Challenge

Pre-print

Talk

Bug-Fixing in the Age of AI: Human vs. Agentic Pull Requests

Mining Challenge

Talk

Why Are AI Agent–Involved Pull Requests (Fix-Related) Remain Unmerged? An Empirical Study

Mining Challenge

Talk

LGTM! Characteristics of Auto-Merged LLM-based Agentic PRs

Mining Challenge

DOI Pre-print Media Attached

Talk

Do AI-Generated Pull Requests Get Rejected More? (Yes but Why?)

Mining Challenge

Rosie Wang University of Alberta

,

Zhou Yang University of Alberta, Alberta Machine Intelligence Institute

Talk

How AI Coding Agents Communicate: A Study of Pull Request Characteristics and Human Review Responses

Mining Challenge

Pre-print

Talk

Where Do AI Coding Agents Fail? An Empirical Study of Failed Agentic Pull Requests in GitHub

Mining Challenge

Pre-print

Talk

An Empirical Study of Tests in Agentic Pull Requests

Mining Challenge

DOI Pre-print Media Attached

Talk

Who Said CVE? How Vulnerability Identifiers Are Mentioned by Humans, Bots, and Agents in Pull Requests

Mining Challenge

Talk

Behavioral Analysis of AI Code Generation Agents: Edit, Rewrite, and Repetition

Mining Challenge

Talk

A Study on Code Clone Lifecycles in Pull Requests Created by AI Agents

Mining Challenge

Talk

On Autopilot? An Empirical Study of Human–AI Teaming and Review Practices in Open Source

Mining Challenge

Talk

From Industry Claims to Empirical Reality: An Empirical Study of Code Review Agents in Pull Requests

Mining Challenge

DOI Pre-print File Attached

Talk

A Study of Library Usage in Agent-Authored Pull Requests

Mining Challenge

DOI Pre-print

Talk

Studying the Footprints of AI Coding Agents in Blockchain Repositories

Mining Challenge

Talk

Human-Agent versus Human Pull Requests: A Testing-Focused Characterization and Comparison

Mining Challenge

DOI Pre-print

Talk

Do AI Agents Really Improve Code Readability?

Mining Challenge

Talk

When is Generated Code Difficult to Comprehend? Assessing AI Agent Python Code Proficiency in the Wild

Mining Challenge

Pre-print

Talk

How do Agents Refactor: An Empirical Study

Mining Challenge

Pre-print

Talk

An Empirical Analysis of Test Failures in AI-Generated Pull Requests

Mining Challenge

Media Attached File Attached