AISM 2025 Logo

The 1st International Workshop on AI for Software Modernization

20th November, 2025, Seoul, South Korea

To be held in conjunction with the 40th IEEE/ACM International Conference on Automated Software Engineering (ASE 2025)

Introduction

Application modernization is the process of upgrading software applications to enhance technology, accommodate evolving dependencies, adopt modern architectures and programming languages, and meet new business requirements. Research estimates suggest that modernization accounts for 80% of software maintenance costs, highlighting the urgent need for automation and AI-driven solutions to reduce manual effort, lower costs, and improve accuracy.

Common modernization efforts include:

While modernization is essential, it presents significant challenges, such as preserving application semantics, estimating transformation effort, and ensuring correctness after refactoring. This workshop focuses on the role of AI in software modernization. Submissions that advance traditional techniques for software modernization are also welcome.

Keynote Talks

Ahmed E. Hassan

The Agentic Software Engineering Revolution

Speaker: Ahmed E. Hassan, Queen’s University, Canada

Abstract: The fundamentals of software and software engineering are undergoing a significant transformation. This talk introduces AIware (AI-Powered Software), and explores the emergence of Agentic Software Engineering. We'll discuss how to move beyond informal “vibe coding” towards “vibe engineering” and ultimately to “Agentic SE” — a more disciplined and powerful framework for creating production-grade software.

This talk will explore a future where the developer's role evolves from simply writing code to becoming an orchestrator, collaborator, and mentor for AI teammates as we move beyond the era of simple "copilots" into one of a more dynamic, collaborative partnership between humans and AI. We will ground this vision in findings from our analysis of AIDev, a large-scale dataset of ~1 Million agent-generated pull requests. We will highlight what real agentic work looks like in the wild, revealing both the impressive potential and the practical challenges that lie ahead.

Join me to discover how we can build systems of greater complexity and scale through conversation, intent, and creative partnership with AI. This is a chance to understand the foundational principles of this emerging field and to prepare for the next revolution in technology.

For those eager to get a preview of the foundational pillars of this new era, you can explore the core concepts in our recent paper: https://arxiv.org/abs/2509.06216

Bio: Ahmed E. Hassan is a Mustafa Prize Laureate, an honor widely equated to a Nobel-level recognition, and a Fellow of ACM, IEEE, and AAIA, as well as an NSERC Steacie Fellow, Canada’s most prestigious mid-career research award across all fields of science and engineering. He holds the Canada Research Chair and the NSERC/BlackBerry Industrial Research Chair in Software Engineering at Queen’s University and is among the world’s most cited Software Engineering researchers. He is the only individual to receive both the ACM SIGSOFT Influential Educator Award (2019) and the IEEE TCSE Distinguished Educator Award (2020), the highest honors for SE educators from the world’s two largest professional societies. As the founder of the AI-Augmented SE, MSR, and AIware communities and a member of the Royal Society of Canada, his career spans over three decades, including leadership roles in both industrial research (IBM Almaden, BlackBerry) and academia.

Marco Vieira

Benchmarking GenAI for Software Engineering: Challenges and Insights

Speaker: Marco Vieira, University of North Carolina at Charlotte, USA

Abstract: GenAI is rapidly reshaping software engineering, advancing capabilities in code generation, translation, testing, and issue analysis. However, current evaluation practices remain fragmented, inconsistent, and often irreproducible, making it difficult to assess genuine progress. In this talk, we will explore the challenges of systematically and transparently benchmarking GenAI for software engineering. We will present a unified framework that integrates key components (metrics, workloads, prompting strategies, and experimental procedures) to enable rigorous and comparable assessments across diverse tasks. Through practical examples, we will demonstrate how to achieve trustworthy, evidence-based, and reproducible evaluations of Large Language Models (LLMs) for software development.

Bio: Marco Vieira is a Professor in the College of Computing and Informatics at the University of North Carolina at Charlotte. He received his Ph.D. in Informatics Engineering from the University of Coimbra, Portugal. His research interests include dependability and security assessment and benchmarking, fault injection, failure prediction, static analysis, and software testing. Marco has authored or co-authored over 270 papers in refereed journals and international conferences and has led or participated in numerous national and international research projects. He currently serves as chair of IFIP Working Group 10.4 on Dependable Computing and Fault Tolerance, as an Associate Editor of IEEE TDSC, as vice-chair of the IEEE/IFIP DSN steering committee, and as a member of the steering committees for ISSRE, SRDS, and LADC. His current work focuses on leveraging LLMs to support software engineering, including software vulnerability detection, bug report analysis and management, code generation, code translation, test case generation, and trustworthiness assessment.

Important Dates

Call for Papers

We invite high-quality, original research contributions, including but not limited to the following areas:

1. Application Understanding

2. Modernization Design and Effort Estimation

3. Application Transformation

4. Testing, Debugging, and Repair

5. Case Studies and Applications

Evaluation Criteria

Submission Guidelines

Proceedings

All accepted papers will be included in the ASE 2025's conference proceedings. The proceedings will be made available online and indexed in the ACM/IEEE Digital Library.

Organizers

Committee

Accepted Papers

Program

Updated here