AIware 2025
Wed 19 - Thu 20 November 2025
co-located with ASE 2025
You're viewing the program in a time zone which is different from your device's time zone change time zone

Wed 19 Nov

Displayed time zone: Seoul change

09:00 - 09:20
OpeningMain Track at Grand Hall 1
Chair(s): Yiling Lou University of Illinois at Urbana-Champaign, Qinghua Lu Data61, CSIRO, Jie M. Zhang King's College London
09:20 - 10:30
AIware & SecurityMain Track at Grand Hall 1
Chair(s): Weiyi Shang University of Waterloo
09:20
8m
Talk
CHASE: LLM Agents for Dissecting Malicious PyPI Packages
Main Track
Takaaki Toda Waseda University, Tatsuya Mori Waseda University
File Attached
09:28
8m
Talk
CFCEval: Evaluating Security Aspects in Code Generated by Large Language Models
Main Track
Cheng Cheng Concordia University, Jinqiu Yang Concordia University
Pre-print
09:36
8m
Talk
Security in the Wild: An Empirical Analysis of LLM-Powered Applications and Local Inference Frameworks
Main Track
Julia Gomez-Rangel Texas A&M University - Corpus Christi, Young Lee Texas A & M University - San Antonio, Bozhen Liu Texas A&M University - Corpus Christi
Pre-print
09:44
8m
Talk
How Quantization Impacts Privacy Risk on LLMs for Code?
Main Track
Md Nazmul Haque North Carolina State University, Hua yang North Carolina State University, Zhou Yang University of Alberta, Alberta Machine Intelligence Institute , Bowen Xu North Carolina State University
Pre-print
09:52
8m
Talk
Securing the Multi-Chain Ecosystem: A Unified, Agent-Based Framework for Vulnerability Repair in Solidity and Move
Main Track
Rabimba Karanjai University of Houston, Lei Xu Kent State University, Weidong Shi University of Houston
10:00
8m
Talk
SEALGuard: Safeguarding the Multilingual Conversations in Southeast Asian Languages for AI-Powered Software
Main Track
Wenliang Shan Monash University, Michael Fu The University of Melbourne, Rui Yang Monash University and Transurban, Kla Tantithamthavorn Monash University and Atlassian
Pre-print File Attached
10:10
20m
Live Q&A
Joint Q&A and Discussion #AISecurity
Main Track

11:00 - 12:30
AIware Keynotes Session 1Keynotes at Grand Hall 1
Chair(s): Jie M. Zhang King's College London
11:00
20m
Keynote
Claude Code: From Single Agent in Terminal to Multi-Agent Systems
Keynotes
K: Dickson Tsai Anthropic
11:20
20m
Keynote
Code assistants: from code completion to coding agents
Keynotes
K: Baptiste Rozière Mistral AI
Pre-print
11:40
20m
Keynote
Demystifying LLM-based Software Engineering Agents
Keynotes
K: Lingming Zhang University of Illinois at Urbana-Champaign
Pre-print
12:00
30m
Panel
Joint Q&A and Discussion
Keynotes

14:00 - 15:30
AIware Keynotes Session 2Keynotes at Grand Hall 1
Chair(s): Yiling Lou University of Illinois at Urbana-Champaign
14:00
20m
Keynote
Gemini CLI: The Terminal Renaissance
Keynotes
K: Taylor Mullen Google
Pre-print
14:20
20m
Keynote
Ambient, Safe Agentic Automation on the GitHub Platform
Keynotes
K: Don Syme Microsoft
Pre-print
14:40
20m
Keynote
Human To Hero: How Gen AI Can Be The Alfred That Transforms Anyone Into Batman
Keynotes
K: Jack Johns BT Group PLC
15:00
30m
Panel
Joint Q&A and Discussion
Keynotes

16:00 - 16:50
Human Factors and Organizational Perspectives in AIwareMain Track at Grand Hall 1
Chair(s): Hongyu Zhang Chongqing University
16:00
8m
Research paper
Examining the Usage of Generative AI Models in Student Learning Activities for Software Programming
Main Track
Rufeng Chen McGill University, Shuaishuai Jiang , Jiyun Shen , AJung Moon McGill University, Lili Wei McGill University
Pre-print
16:08
8m
Talk
Human to Document, AI to Code: Three Case Studies of Comparing GenAI for Notebook Competitions
Main Track
Tasha Settewong Nara Institute of Science and Technology, Youmei Fan Nara Institute of Science and Technology, Raula Gaikovina Kula The University of Osaka, Kenichi Matsumoto Nara Institute of Science and Technology
Pre-print
16:16
8m
Talk
Judge the Votes: A System to Classify Bug Reports and Give Suggestions
Main Track
Emre Dinc Bilkent University, Eray Tüzün Bilkent University
Pre-print
16:24
8m
Talk
Model-Assisted and Human-Guided: Perceptions and Practices of Software Professionals Using LLMs for Coding
Main Track
Italo Santos University of Hawai‘i at Mānoa, Cleyton Magalhaes Universidade Federal Rural de Pernambuco, Ronnie de Souza Santos University of Calgary
Pre-print
16:32
18m
Live Q&A
Joint Discussion #HumanInTheLoop
Main Track

16:50 - 17:35
Emerging Frontiers and Applications of AIwareMain Track / ArXiv Track at Grand Hall 1
Chair(s): Cuiyun Gao Harbin Institute of Technology, Shenzhen
16:50
5m
Talk
Envisioning Future Interactive Web Development: Editing Webpage with Natural Language
Main Track
Dang Truong Singapore Management University, Jingyu Xiao The Chinese University of Hong Kong, Yintong Huo Singapore Management University, Singapore
16:55
5m
Talk
On the Promises and Challenges of AI-Powered XR Glasses as Embodied Software
Main Track
Ruizhen Gu University of Sheffield, Jingqiong Zhang University of Sheffield, José Miguel Rojas University of Sheffield, Donghwan Shin University of Sheffield
Pre-print
17:00
5m
Talk
Multi-Objective Reinforcement Learning for Critical Scenario Generation of Autonomous Vehicles
ArXiv Track
Jiahui Wu Simula Research Laboratory and University of Oslo, Chengjie Lu Simula Research Laboratory and University of Oslo, Aitor Arrieta Mondragon University, Shaukat Ali Simula Research Laboratory and Oslo Metropolitan University
Pre-print
17:05
5m
Talk
Combining Reasoning Optimized LLMs and SMT Solvers for Automated Loop Invariant Synthesis
Main Track
17:10
5m
Talk
Evaluating Large Language Models for Code Translation: Effects of Prompt Language and Prompt Design
ArXiv Track
17:15
20m
Live Q&A
Joint Q&A and Discussion #AIwareApplications
Main Track

17:35 - 18:20
Brainstorming Panel 1: Future of SE agents and Workflow Main Track at Grand Hall 1
Chair(s): Ahmed E. Hassan Queen’s University

Thu 20 Nov

Displayed time zone: Seoul change

08:30 - 10:00
AIware Keynotes Session 3Keynotes at Grand Hall 1
Chair(s): Gustavo Oliva Centre for Software Excellence, Huawei Canada
08:30
20m
Keynote
Spec Kit in Practice: Executable Specs, On‑Demand Checklists, and a Polya Loop
Keynotes
K: John Lam Microsoft
Pre-print
08:50
20m
Keynote
Automatically Maintaining Agent Systems: How Far Are We?
Keynotes
K: Yiling Lou University of Illinois at Urbana-Champaign
09:10
20m
Keynote
Teaching LLMs to Debug: Toward Reasoning- and Tool-Aware Coding Agents
Keynotes
K: Chao Peng ByteDance
09:30
30m
Panel
Joint Q&A and Discussion
Keynotes

10:30 - 11:50
LLM-Based Software Testing and Quality AssuranceMain Track / Benchmark & Dataset Track at Grand Hall 1
Chair(s): Xiaoning Du Monash University
10:30
8m
Talk
Understanding the Characteristics of LLM-Generated Property-Based Tests in Exploring Edge Cases
Main Track
Hidetake Tanaka Nara Institute of Science and Technology, Haruto Tanaka Nara Institute of Science and Technology, Kazumasa Shimari Nara Institute of Science and Technology, Kenichi Matsumoto Nara Institute of Science and Technology
Pre-print
10:38
8m
Talk
Understanding LLM-Driven Test Oracle Generation
Main Track
Adam Bodicoat University of Auckland, Gunel Jahangirova King's College London, Valerio Terragni University of Auckland
10:46
8m
Talk
Turning Manual Tasks into Actions: Assessing the Effectiveness of Gemini-generated Selenium Tests
Main Track
Myron David Peixoto Federal University of Alagoas, Baldoino Fonseca Universidade Federal de Alagoas, Davy Baía Federal University of Alagoas, Kevin Lira North Carolina State University, Márcio Ribeiro Federal University of Alagoas, Brazil, Wesley K.G. Assunção North Carolina State University, Nathalia Nascimento Pennsylvania State University, Paulo Alencar University of Waterloo
File Attached
10:54
8m
Talk
Software Testing with Large Language Models: An Interview Study with Practitioners
Main Track
Maria Deolinda Cesar school, Cleyton Magalhaes Universidade Federal Rural de Pernambuco, Ronnie de Souza Santos University of Calgary
11:02
8m
Talk
HPCAgentTester: A Multi-Agent LLM Approach for Enhanced HPC Unit Test Generation
Main Track
Rabimba Karanjai University of Houston, Lei Xu Kent State University, Weidong Shi University of Houston
11:10
8m
Talk
Assertion-Aware Test Code Summarization with Large Language Models
Benchmark & Dataset Track
Anamul Haque Mollah University of North Texas, Ahmed Aljohani University of North Texas, Hyunsook Do University of North Texas
DOI Pre-print
11:20
30m
Live Q&A
Joint Q&A and Discussion #LLMforTesting
Main Track

11:50 - 12:30
Future of AIwareBenchmark & Dataset Track / Main Track / ArXiv Track at Grand Hall 1
Chair(s): Haoye Tian Aalto University
11:50
8m
Talk
The Future of Generative AI in Software Engineering: A Vision from Industry and Academia in the European GENIUS Project
Main Track
Robin Gröpler ifak - Institute for Automation and Communication, Magdeburg, Steffen Klepke Siemens AG, Jack Johns BT Group PLC, Andreas Dreschinski Akkodis, Klaus Schmid , Benedikt Dornauer University of Innsbruck; University of Cologne, Eray Tüzün Bilkent University, Joost Noppen , Mohammad Reza Mousavi King's College London, Yongjian Tang Siemens AG, Germany, Johannes Viehmann Fraunhofer FOKUS, Germany, Selin Şirin Aslangül , Beum Seuk Lee BT Group PLC, Adam Ziolkowski BT, Eric Zie
Pre-print
11:58
5m
Talk
Where Do LLMs Still Struggle? An In-Depth Analysis of Code Generation Benchmarks
Benchmark & Dataset Track

12:03
5m
Talk
Guidelines for Empirical Studies in Software Engineering involving Large Language Models
ArXiv Track
Sebastian Baltes Heidelberg University, Florian Angermeir fortiss GmbH, Chetan Arora Monash University, Marvin Muñoz Barón Technical University of Munich, Chunyang Chen TU Munich, Lukas Böhme Hasso Plattner Institute, University of Potsdam, Potsdam, Germany, Fabio Calefato University of Bari, Neil Ernst University of Victoria, Davide Falessi University of Rome Tor Vergata, Italy, Brian Fitzgerald Lero - The Irish Software Research Centre and University of Limerick, Davide Fucci Blekinge Institute of Technology, Marcos Kalinowski Pontifical Catholic University of Rio de Janeiro (PUC-Rio), Stefano Lambiase Department of Computer Science, Aalborg University, Denmark, Daniel Russo Department of Computer Science, Aalborg University, Mircea Lungu IT University, Copenhagen, Lutz Prechelt Freie Universität Berlin, Paul Ralph Dalhousie University, Christoph Treude Singapore Management University, Stefan Wagner Technical University of Munich
Pre-print
12:10
20m
Live Q&A
Joint Q&A and Discussion #FutureofAIware
Main Track

14:00 - 15:00
AIware Keynotes Session 4Keynotes at Grand Hall 1
Chair(s): Ahmed E. Hassan Queen’s University
14:00
20m
Keynote
Unlocking the Potential of LLMs with Care: Can They Really Understand Code Changes?
Keynotes
K: Patanamon Thongtanunam The University of Melbourne
14:20
20m
Keynote
AIware: Beyond Correctness
Keynotes
K: Jie M. Zhang King's College London
14:40
20m
Panel
Joint Q&A and Discussion
Keynotes

15:00 - 15:29
Evaluation Frameworks, and Quantitative Assessment of LLMs (Part 1)Benchmark & Dataset Track / Main Track at Grand Hall 1
Chair(s): Zhou Yang University of Alberta, Alberta Machine Intelligence Institute
15:00
8m
Talk
Automated Extract Method Refactoring with Open-Source LLMs: A Comparative Study
Main Track
Sivajeet Chand Technical University of Munich, Melih Kilic Technical University of Munich, Roland Würsching Technical University of Munich, Sushant Kumar Pandey University of Groningen, The Netherlands, Alexander Pretschner TU Munich
Pre-print
15:08
8m
Talk
Benchmarking Web API Integration Code Generation
Benchmark & Dataset Track
Daniel Maninger TU Darmstadt, Leon Chemnitz TU Darmstadt, Amir Molzam Sharifloo , Mira Mezini TU Darmstadt; hessian.AI; National Research Center for Applied Cybersecurity ATHENE
Pre-print
15:16
8m
Talk
From Search to Reasoning: A Five-Level RAG Capability Framework for Enterprise Data
Benchmark & Dataset Track
Gurbinder Gill , Ritvik Gupta Carnegie Mellon University, USA, Denis Lusson , Anand Chandrashekar , Donald Nguyen Corvic AI
Pre-print
15:24
5m
Talk
SWE-Sharp-Bench: A Reproducible Benchmark for C# Software Engineering Tasks
Benchmark & Dataset Track
Sanket Mhatre Microsoft, Yasharth Bajpai Microsoft, Sumit Gulwani Microsoft, Emerson Murphy-Hill Microsoft, Gustavo Soares Microsoft
Pre-print
16:00 - 16:50
Evaluation Frameworks, and Quantitative Assessment of LLMs (Part 2)Main Track / Benchmark & Dataset Track at Grand Hall 1
Chair(s): Zhou Yang University of Alberta, Alberta Machine Intelligence Institute
16:00
8m
Talk
PromptExp: Multi-granularity Prompt Explanation of Large Language Models
Main Track
Ximing Dong Centre for Software Excellence at Huawei Canada, Shaowei Wang University of Manitoba, Dayi Lin Centre for Software Excellence, Huawei Canada, Gopi Krishnan Rajbahadur Centre for Software Excellence, Huawei, Canada, Ahmed E. Hassan Queen’s University
16:08
8m
Talk
Beyond Code Explanations: A Ray of Hope for Cross-Language Vulnerability Repair
Main Track
Kevin Lira North Carolina State University, Baldoino Fonseca Universidade Federal de Alagoas, Wesley K.G. Assunção North Carolina State University, Davy Baía Federal University of Alagoas, Márcio Ribeiro Federal University of Alagoas, Brazil
Pre-print
16:16
8m
Talk
Secure Code Generation at Scale with Reflexion
Benchmark & Dataset Track
Arup Datta University of North Texas, Ahmed Aljohani University of North Texas, Hyunsook Do University of North Texas
Pre-print
16:24
5m
Talk
A Tool for Benchmarking Large Language Models' Robustness in Assessing the Realism of Driving Scenarios
Benchmark & Dataset Track
Jiahui Wu Simula Research Laboratory and University of Oslo, Chengjie Lu Simula Research Laboratory and University of Oslo, Aitor Arrieta Mondragon University, Shaukat Ali Simula Research Laboratory and Oslo Metropolitan University
Pre-print
16:29
21m
Live Q&A
Joint Q&A and Discussion #LLMAssessment
Main Track

16:50 - 17:35
Responsible, Ethical, and Legal Dimensions of AIwareMain Track at Grand Hall 1
Chair(s): Jingzhi Gong
16:50
8m
Talk
Neuro-Symbolic Compliance: Integrating LLMs and SMT for Automated Financial Legal Analysis
Main Track
Yung Shen HSIA National Chengchi University, Fang Yu National Chengchi University, Jie-Hong Roland Jiang National Taiwan University
File Attached
16:58
8m
Talk
Are We Aligned? A Preliminary Investigation of the Alignment of Responsible AI Values between LLMs and Human Judgment
Main Track
Asma Yamani King Fahd University of Petroleum and Minerals, Malak Baslyman King Fahd University of Petroleum & Minerals, Moataz Ahmed King Fahd University of Petroleum and Minerals
File Attached
17:06
5m
Talk
A Vision for Value-Aligned AI-Driven Systems
Main Track
Humphrey Obie Monash University
17:11
5m
Talk
Generative AI and Empirical Software Engineering: A Paradigm Shift
Main Track
Christoph Treude Singapore Management University, Margaret-Anne Storey University of Victoria
Pre-print
17:16
19m
Live Q&A
Joint Discussion #ResponsibleAI
Main Track

17:35 - 18:20
Brainstorming Panel 2: Critical Challenges in AIware & Possible SolutionsMain Track at Grand Hall 1
Chair(s): Dayi Lin Centre for Software Excellence, Huawei Canada
18:20 - 18:40
Awards and ClosingMain Track at Grand Hall 1