5 citations · 12 across the 16 of their papers we have counts for
19 papers
MCP-Eco: A Linked Dataset of MCP Servers, Consumers, and Development Activity
Khalid Tounoussi, Mohammed Sayagh, Ali Ouni +1
The Model Context Protocol (MCP) enables LLM agents to access external tools and data. Studying its software ecosystem requires connecting server interfaces, the projects that conf…
Is Self-Admitted Technical Debt Tested? An Empirical Study of Coverage, Co-change, and Impact
Suzuka Yoshimoto, Kosei Horikawa, Daniel Feitosa +2
When developers write a TODO or FIXME comment, they are explicitly admitting that the code is suboptimal: a built-in warning that this logic deserves extra scrutiny. Yet it is an o…
AgentLogs: A Dataset for Opening the Black Box of Cloud Agents on GitHub
Jonan Richards, Kosei Horikawa, Youmei Fan +2
Coding agents now complete development tasks in real software projects and submit the results as pull requests. A pull request shows the outcome of an agent's execution but not the…
What Are Developers Actually Discussing When Visual Regression Tests Fail?
Miku Watanabe, Kosei Horikawa, Brittany Reid +2
Visual Regression Tests (VRTs) are widely adopted as a mechanism for detecting unintended visual changes in user interfaces. By design, VRTs operate on rendered pixel output, and t…
How Do Developers Maintain and Evolve Their Agents' Instructions? An Empirical Study
Gianmario Voria, Alfonso Cannavale, Andrea De Lucia +3
Context. Autonomous coding agents are increasingly used in software development, shifting parts of the engineering process to AI assistance. While this automation brings clear bene…
To What Extent Does Agent-generated Code Require Maintenance? An Empirical Study
Shota Sawada, Tatsuya Shirai, Yutaro Kashiwa +3
LLM-based autonomous coding agents have reshaped software development. While these agents excel at code generation, open questions persist about the long-term maintainability of AI…
Testing with AI Agents: An Empirical Study of Test Generation Frequency, Quality, and Coverage
Suzuka Yoshimoto, Shun Fujita, Kosei Horikawa +3
Agent-based coding tools have transformed software development practices. Unlike prompt-based approaches that require developers to manually integrate generated code, these agent-b…
Do AI Agents Really Improve Code Readability?
Kyogo Horikawa, Kosei Horikawa, Yutaro Kashiwa +2
Code readability is fundamental to software quality and maintainability. Poor readability extends development time, increases bug-inducing risks, and contributes to technical debt.…
What to Cut? Predicting Unnecessary Methods in Agentic Code Generation
Kan Watanabe, Tatsuya Shirai, Yutaro Kashiwa +1
Agentic Coding, powered by autonomous agents such as GitHub Copilot and Cursor, enables developers to generate code, tests, and pull requests from natural language instructions alo…
Does Programming Language Matter? An Empirical Study of Fuzzing Bug Detection
Tatsuya Shirai, Olivier Nourry, Yutaro Kashiwa +2
Fuzzing has become a popular technique for automatically detecting vulnerabilities and bugs by generating unexpected inputs. In recent years, the fuzzing process has been integrate…
Agentic Refactoring: An Empirical Study of AI Coding Agents
Kosei Horikawa, Hao Li, Yutaro Kashiwa +3
Agentic coding tools, such as OpenAI Codex, Claude Code, and Cursor, are changing how software is developed. These AI-powered systems function as autonomous teammates capable of pl…
Agent READMEs: An Empirical Study of Context Files for Agentic Coding
Worawalan Chatlatanagulchai, Hao Li, Yutaro Kashiwa +8
Agentic coding tools receive goals written in natural language, break them down into specific tasks, and write or execute code with minimal human intervention. Central to this proc…
Large-Scale Empirical Analysis of Continuous Fuzzing: Insights from 1 Million Fuzzing Sessions
Tatsuya Shirai, Olivier Nourry, Yutaro Kashiwa +3
Software vulnerabilities are constantly being reported and exploited in software products, causing significant impacts on society. In recent years, the main approach to vulnerabili…
An Empirical Study of Security-Policy Related Issues in Open Source Projects
Rintaro Kanaji, Brittany Reid, Yutaro Kashiwa +2
GitHub recommends that projects adopt a security file that outlines vulnerability reporting procedures. However, the effectiveness and operational challenges of such files are not…
Detecting and Characterizing Low and No Functionality Packages in the NPM Ecosystem
Napasorn Tevarut, Brittany Reid, Yutaro Kashiwa +4
Trivial packages, small modules with low functionality, are common in the npm ecosystem and can pose security risks despite their simplicity. This paper refines existing definition…
Understanding Self-Admitted Technical Debt in Test Code: An Empirical Study
Ibuki Nakamura, Yutaro Kashiwa, Bin Lin +1
Developers often opt for easier but non-optimal implementation to meet deadlines or create rapid prototypes, leading to additional effort known as technical debt to improve the cod…
On the Use of Agentic Coding Manifests: An Empirical Study of Claude Code
Worawalan Chatlatanagulchai, Kundjanasith Thonglek, Brittany Reid +5
Agentic coding tools receive goals written in natural language as input, break them down into specific tasks, and write/execute the actual code with minimal human intervention. Key…
On the Use of Agentic Coding: An Empirical Study of Pull Requests on GitHub
Miku Watanabe, Hao Li, Yutaro Kashiwa +3
Large language models (LLMs) are increasingly being integrated into software development processes. The ability to generate code and submit pull requests with minimal human interve…
Agentic Software Engineering: Foundational Pillars and a Research Roadmap
Ahmed E. Hassan, Hao Li, Dayi Lin +4
Agentic Software Engineering (SE 3.0) represents a new era where intelligent agents are tasked not with simple code generation, but with achieving complex, goal-oriented SE objecti…