MB 1.210 - AIware 2026

VenueConcordia SGW Campus @Downtown Montreal

Room nameMB 1.210

Floor0

Room InformationNo extra information available

Program

Time Zone

The program is currently displayed in (GMT-04:00) Eastern Time (US & Canada).

Use conference time zone: (GMT-04:00) Eastern Time (US & Canada)Select other time zone

The GMT offsets shown reflect the offsets at the moment of the conference.

Time Band

By setting a time band, the program will dim events that are outside this time window. This is useful for (virtual) conferences with a continuous program (with repeated sessions).
The time band will also limit the events that are included in the personal iCalendar subscription service.

Display full programSpecify a time band

Save

You're viewing the program in a time zone which is different from your device's time zone change time zone

Mon 6 Jul
Displayed time zone: Eastern Time (US & Canada) change

	08:30 - 08:50	OpeningMain Track at MB 1.210 Chair(s): Tse-Hsun (Peter) Chen Concordia University, Chao Peng Tencent, Baishakhi Ray Columbia University

08:50 - 10:30	Coding Agents, Software Testing, and Code UnderstandingArXiv Track / Main Track at MB 1.210 Chair(s): Song Wang York University

08:50 5m Talk		Collaborator or Assistant? How AI Coding Agents Partition Work across Pull Request Lifecycles Main Track Young Jo Chung , Safwat Hassan University of Toronto DOI
08:55 5m Talk		When Code Authors Are Agents: A Large-Scale Study of Human–Agent Collaboration in Pull Requests Main Track Anthonia Oluchukwu Njoku École Polytechnique de Montréal, Université de Montréal, CA, Zohreh Sharafi Polytechnique Montréal, Foutse Khomh Polytechnique Montréal DOI
09:00 5m Talk		Understanding Conversational Patterns in Multi-agent Programming: A Case Study on Fibonacci Game Development Main Track Srijita Basu Chalmers University of Technology and University of Gothenburg, Viktor Kjellberg Göteborg University, SE, Simin Sun , Bengt Haraldsson Chalmers University of Technology and University of Gothenburg, Scania CV AB, Md Abu Ahammed Babu Volvo Cars AB, Wilhelm Meding Ericsson, Farnaz Fotrousi Chalmers University of Technology and University of Gothenburg, Miroslaw Staron Chalmers University of Technology and University of Gothenburg DOI File Attached
09:05 5m Talk		Wink: Recovering from Misbehaviors in Coding Agents Main Track Rahul Nanda Facebook, US, Chandra Maddila Meta Platforms, Inc., Smriti Jha Facebook, US, Euna Mehnaz Khan , Satish Chandra Meta Platforms, Inc., Matteo Paltenghi University of Stuttgart DOI
09:10 5m Talk		Configuring Agentic AI Coding Tools: An Exploratory Study Main Track Matthias Galster University of Canterbury, Seyedmoein Mohsenimofidi Heidelberg University, Jai Lal Lulla Singapore Management University, Muhammad Auwal Abubakar Otto-Friedrich Universität Bamberg, DE, Christoph Treude Singapore Management University, Sebastian Baltes Heidelberg University DOI Pre-print
09:15 5m Talk		Deterministic vs. LLM-Controlled Orchestration for COBOL-to-Python ModernizationAIware Honorable Mention Paper Award Main Track Naing Oo Lwin Bucknell University, US, Rajesh Kumar Bucknell University, US DOI
09:20 5m Talk		Developer Experience with AI Coding Agents: HTTP Behavioral Signatures in Documentation Portals ArXiv Track Oleksii Borysenko Cisco DevNet
09:25 5m Talk		VISOR: A Vision-Language Model-Based Test Oracle for Testing Robots Main Track Prasun Saurabh Simula Research Laboratory, NO, Pablo Valle Mondragon University, Aitor Arrieta Mondragon University, Shaukat Ali Simula Research Laboratory and Oslo Metropolitan University, Paolo Arcaini National Institute of Informatics DOI
09:30 5m Talk		Fixpad++: Automated Bug Fix Verification using LLM AgentsAIware Honorable Mention Paper Award Main Track Mustafa Özkan İr Bilkent University, Bilkent University, TR, Mehmet Dedeler Bilkent University, Anil Koyuncu Bilkent University, Eray Tüzün Bilkent University DOI
09:35 5m Talk		Co-located Tests, Better AI Code: How Test Syntax Structure Affects Foundation Model Code Generation Main Track Éric Jacopin Cosmic AI, FR DOI
09:40 5m Talk		Using Mutation-Analysis to Examine an LLM’s Ability to Summarize Code Main Track Lara Khatib University of Waterloo, Michael Pu University of Waterloo, Bogdan Vasilescu Carnegie Mellon University, Mei Nagappan University of Waterloo DOI
09:45 5m Talk		Testing AIware Systems: A Software Engineering SurveyAIware Honorable Mention Paper Award Main Track Karla Gonzalez Royal Military College of Canada, Mariam El Mezouar Royal Military College DOI
09:50 5m Talk		TestMap: Evidence Infrastructure for Foundation-Model-Assisted Test Generation ArXiv Track Hunter Leary Virginia Tech, Luke Hanuska Virginia Tech, Chris Brown Virginia Tech
09:55 5m Talk		Metamorphic Testing for Clinical ML Models: A Framework Proposal and Pilot Study ArXiv Track Jie JW Wu Michigan Technological University, USA, Feiyu E Michigan Technological University, USA, Bo Chen Michigan Technological University, USA
10:00 5m Talk		An Empirical Study of Reasoning Steps in Thinking Code LLMsAIware Honorable Mention Paper Award Main Track Haoran Xue York University, CA, Gias Uddin York University, Canada, Song Wang York University DOI
10:05 5m Talk		Can LLMs Really Reason about Code? Studying How Well LLMs Understand the Relation between Input, Code, and Output Main Track Norman Becker CISPA Helmholtz Center for Information Security, DE, Tural Mammadov CISPA Helmholtz Center for Information Security, Andreas Zeller CISPA Helmholtz Center for Information Security Link to publication DOI File Attached
10:10 5m Talk		How Robustly Do LLMs Understand Execution Semantics? Main Track Claudio Spiess University of California, Davis, Premkumar Devanbu UC Davis, Earl T. Barr University College London DOI
10:15 5m Talk		Program-as-Weights: A Programming Paradigm for Fuzzy Functions ArXiv Track Wentao Zhang University of Waterloo, Liliana Hotsko University of Waterloo, Woojeong Kim Cornell University, Pengyu Nie University of Waterloo, Stuart Shieber Harvard University, Yuntian Deng University of Waterloo Pre-print
10:20 10m Live Q&A		Joint Q&A Main Track

11:00 - 12:30	AIware Keynotes Session 1Keynotes / Main Track at MB 1.210 Chair(s): Chao Peng Tencent

11:00 20m Keynote		From Chatbots to Colleagues: Steering Code-Driven Agents for End-to-End Autonomy Keynotes K: Qidi Xu MiniMax
11:20 20m Keynote		When Implementation Stops Being the Bottleneck: Design in AI-Native Software Engineering Keynotes K: Thomas Cottenier Arm
11:40 20m Keynote		From Features to Data and Domain Knowledge: Reflections on Two Decades of AI for Software Keynotes K: Lin Tan Purdue University
12:00 30m Live Q&A		Joint Q&A Keynotes

14:00 - 15:30	Trustworthy Code Generation, Reliability, and Engineering of AIware SystemsMain Track at MB 1.210 Chair(s): Zhijie Wang Concordia University

14:00 5m Talk		VeriTrans: Fine-Tuned LLM-Assisted NL→PL Translation via a Deterministic Neuro-symbolic Pipeline Main Track Xuan Liu , Dheeraj Kodakandla Pennsylvania State University, US, Kushagra Srivastva Pennsylvania State University, US, Mahfuza Farooque Pennsylvania State University, US DOI
14:05 5m Talk		Kubernetes Misconfigurations in the Wild: Taxonomy, Evolution, and Automated Repair with Large Language Models Main Track GHORAB Mostafa Anouar Université Laval, CA, Ahmad Abdellatif University of Calgary, Mohamed Aymen saied Laval University DOI
14:10 5m Talk		Quality and Security Signals in AI-Generated Python Refactoring Pull RequestsAIware Honorable Mention Paper Award Main Track Mohamed Almukhtar University of Michigan-Flint, Anwar Ghammam University of Michigan - Dearborn, Hua Ming DOI Pre-print
14:15 5m Talk		From Assistance to Agency: Rethinking Autonomy and Control in CI/CD Pipelines Main Track Marcus Barnes University of Toronto, Taher A. Ghaleb Trent University, Safwat Hassan University of Toronto DOI Pre-print
14:20 5m Talk		Beyond Translation Accuracy: Addressing False Failures in LLM-Based Code Translation Main Track Fazle Rabbi Concordia University, Soumit Kanti Saha Concordia University, CA, Jinqiu Yang Concordia University DOI
14:25 5m Talk		Executable but Unlearnable: Designing Code That Resists LLM-Based Learning Main Track Viraaji Mothukuri Kennesaw State University, Reza M. Parizi Kennesaw State University DOI
14:30 5m Talk		Detecting Unsoundness in Neural Network Verifiers via Concrete–Abstract Consistency Main Track Kaijie Liu University of New South Wales, Sydney, Yulei Sui University of New South Wales DOI Pre-print
14:35 5m Talk		From Correctness to Consistency: Redefining Reliability for the Agentware Era Main Track Xue Qin Villanova University, Mauricio Gouvea Gruppi DOI
14:40 5m Talk		A Preliminary Study on Explaining Risk of Code Changes using LLM-Based Prediction Models Main Track Yalin Liu Facebook, US, Kosay Jabre Meta Platforms, Inc., Rui Abreu Meta, Zachariah J Carmichael Facebook, US, Vijayaraghavan Murali Rice University, Akshay Patel Meta Platforms, Inc., Jun Ge Meta Platforms, Inc., Weiyan Sun Meta Platforms, Inc., Cong Zhang Southern Methodist University, Southern Methodist University, US, Audris Mockus The University of Tennessee, Knoxville / Vilnius University, David Khavari , Peter Rigby Concordia University; Meta, Nachiappan Nagappan Meta Platforms, Inc. DOI
14:45 5m Talk		When AI Coding Assistants Leak Training Data: A Study of LLM Memorization in Code GenerationAIware Honorable Mention Paper Award Main Track Xiaoyu Cheng , Kundi Yao Ontario Tech University, Pengyu Nie University of Waterloo, Weiyi Shang University of Waterloo DOI
14:50 5m Talk		Zombie Agents: Detecting Semantic Livelock in Long-Horizon Autonomous Software Main Track Simarjot Khanna DOI
14:55 5m Talk		Neural-Symbolic Multi-objective Optimization for Performance-Aware ORM Database Design Main Track Sasan Azizian Bellevue University, Ayoub Hazrati The Vanguard Group, Artin Azizian McGill University, School of Computer Science, Elham Rastegari Creighton University, Hamid Bagheri University of Nebraska-Lincoln, Juan Cui University of Nebraska, Lincoln, US DOI
15:00 5m Talk		TriORM: Workload-Aware Neural-Symbolic Multi-objective Optimization for ORM Mapping Design Main Track Sasan Azizian Bellevue University, Ayoub Hazrati The Vanguard Group, Artin Azizian McGill University, School of Computer Science, Elham Rastegari Creighton University DOI
15:05 5m Talk		Artifact Readiness Gates with Saturation Stop Rules and Host-Parity Admissibility for FM Release Evaluation Main Track Yanick Kanyiki InvarLock Inc., CA DOI
15:10 5m Talk		Towards Migrating Neural Network ImplementationsAIware Honorable Mention Paper Award Main Track Nadia Daoudi Luxembourg Institute of Science and Technology, Iván Alfonso Luxembourg Institute of Science and Technology, Jordi Cabot Luxembourg Institute of Science and Technology DOI
15:15 5m Talk		From Code Review to Spec-Driven Contracts: A Vision for Auditable AIWare Systems Main Track Mohammad Hamdaqa Polytechnique Montreal, Moataz Chouchen Concordia University DOI
15:20 10m Live Q&A		Joint Q&A Main Track

	16:00 - 17:00	Poster Session AMain Track at MB 1.210

	17:00 - 17:45	Brainstorming Panel 1: Model Capability and the Future of Agent HarnessesMain Track at MB 1.210 Chair(s): Hao Li Queen's University We are honored to host the following experts for an in-depth discussion and exchange of ideas: Dickson Tsai, (Claude Code) Pascal Kesseli, (Microsoft) Tse-Hsun (Peter) Chen, (Concordia University) Chao Peng, (Tencent)

Tue 7 Jul
Displayed time zone: Eastern Time (US & Canada) change

11:00 - 12:00	AIware Keynotes Session 2Keynotes / Main Track at MB 1.210 Chair(s): Baishakhi Ray Columbia University

11:00 20m Keynote		Formal Methods for Reliable AI Reasoning Keynotes K: Pascal Kesseli Microsoft
11:20 20m Keynote		Spec-Driven Development for Autonomous Coding Agents Across the SDLC Keynotes K: Rajdeep Mukherjee Amazon, USA
11:40 20m Live Q&A		Joint Q&A Keynotes

12:00 - 12:30	Benchmarks, Datasets, and Evaluation of AIware Benchmark & Dataset Track / ArXiv Track / Main Track at MB 1.210 Chair(s): Mohammad Hamdaqa Polytechnique Montreal

12:00 5m Talk		ClassEval-Pro: A Cross-Domain Benchmark for Class-Level Code Generation Benchmark & Dataset Track Yeheng Chen Shanghai Jiao Tong University, Chaoxiang Xie Hohai University, Yuling Shi Shanghai Jiao Tong University, Wenhao Zeng Shanghai Jiao Tong University, Yongpan Wang Shanghai Jiaotong University, CN, Hongyu Zhang Chongqing University, Xiaodong Gu Shanghai Jiao Tong University DOI
12:05 5m Talk		SWE-Bench+: Enhanced LLM Coding Benchmark Benchmark & Dataset Track Haoran Xue York University, CA, Reem Aleithan York University, Canada, Nafid Enan York University, CA, Gias Uddin York University, Canada, Song Wang York University DOI
12:10 5m Talk		Do Agents Dream of Root Shells? Partial-Credit Evaluation of LLM Agents in Capture the Flag Challenges Benchmark & Dataset Track Ali Al-Kaswan Delft University of Technology, Netherlands, Maksim Plotnikov Delft University of Technology, NL, Maxim Hájek Delft University of Technology, NL, Roland Vízner Delft University of Technology, NL, Arie van Deursen TU Delft, Mali Izadi Google & TU Delft DOI
12:15 5m Talk		A Dataset of Agentic AI Coding Tool Configurations Benchmark & Dataset Track Matthias Galster University of Canterbury, Seyedmoein Mohsenimofidi Heidelberg University, Levi Böhme Universität Bayreuth, DE, Jai Lal Lulla Singapore Management University, Muhammad Auwal Abubakar Otto-Friedrich Universität Bamberg, DE, Christoph Treude Singapore Management University, Sebastian Baltes Heidelberg University DOI
12:20 5m Talk		AgenticFlict: A Large-Scale Dataset of Merge Conflicts in AI Coding Agent Pull Requests on GitHub Benchmark & Dataset Track Daniel Ogenrwot University of Nevada Las Vegas, John Businge University of Nevada, Las Vegas DOI Pre-print
12:25 5m Talk		TestEvo-Bench: An Executable and Live Benchmark for Test and Code Co-Evolution ArXiv Track Jiale Amber Wang University of Waterloo, Kaiyuan Wang Google, Inc., Pengyu Nie University of Waterloo Pre-print

14:00 - 15:30	Human Factors, Responsible AIware, and Benchmarks & DatasetsBenchmark & Dataset Track / Main Track at MB 1.210 Chair(s): Diego Elias Costa Concordia University, Canada

14:00 5m Talk		Is Artificial Intelligence an Elixir to the Software Engineering Community? An Empirical Study among Managers Main Track Xin Zhao Seattle University, Brian Vu Seattle University, US, Sitesh Pattanaik Donald Bren School of Information and Computer Sciences, University of California, Irvine, US DOI
14:05 5m Talk		Towards AI as a Collaborative Partner: A Taxonomy of AI Agent Behavior in Software Engineering Main Track Tao Dong Google, Sherry Shi Google, Harini Sampath , Andrew Macvean Google, Inc. DOI Pre-print
14:10 5m Talk		Auditing Who Appears to Belong: A Large-Scale Empirical Study of Bias in Deployed Text-to-Image Systems for Software Engineering Main Track Mohamad Kassab Boston University DOI
14:15 5m Talk		Operationalizing Ethics for AI Agents: How Developers Encode Values into Repository Context Files Main Track Christoph Treude Singapore Management University, Sebastian Baltes Heidelberg University, Marc Cheong the University of Melbourne DOI Pre-print
14:20 5m Talk		Accountable Agents in Software Engineering: An Analysis of Terms of Service and a Research Roadmap Main Track Christoph Treude Singapore Management University DOI Pre-print
14:25 5m Talk		SOSecure: The Wisdom of the Crowd for Safer AI-Generated Code Main Track Manisha Mukherjee Carnegie Mellon University, Vincent J. Hellendoorn Google DeepMind DOI
14:30 5m Talk		SecVulEval: Context-Aware Benchmarking of LLMs for Vulnerability DetectionAIware Best Benchmark/Dataset Paper Award Benchmark & Dataset Track Md Basim Uddin Ahmed York University, CA, Nima Shiri Harzevili York University, Jiho Shin York University, Hung Viet Pham York University, Song Wang York University DOI
14:35 5m Talk		SecMutBench: Evaluating LLM-Generated Security Tests via Mutation-Based Vulnerability Detection Benchmark & Dataset Track Mariam ALMutairi Virginia Polytechnic Institute and State University, US DOI
14:40 5m Talk		CrossCommitVuln-Bench: A Dataset of Multi-commit Python Vulnerabilities Invisible to Per-Commit Static Analysis Benchmark & Dataset Track Arunabh Majumdar Independent Researcher, IN DOI
14:45 5m Talk		REBench: A Procedural, Fair-by-Construction Benchmark for LLMs on Stripped-Binary Types and Names Benchmark & Dataset Track Jun Yeon Won Ohio State University, Columbus, US, Xin Jin Meta, Shiqing Ma University of Massachusetts at Amherst, Zhiqiang Lin The Ohio State University DOI
14:50 5m Talk		RustBuildEq: A Benchmark for Binary Equivalence under Build Variability Benchmark & Dataset Track Elliott Wen The University of Auckland, Chenye Ni , Valerio Terragni University of Auckland, Jens Dietrich Victoria University of Wellington DOI
14:55 5m Talk		TOGBench: A Developer-Written Multi-variant Dataset and Benchmark Suite for Test Oracle Generation Benchmark & Dataset Track Tasfia Tasnim University of Texas at Dallas, US, Matthew B Dwyer University of Virginia, Soneya Binta Hossain University of Texas at Dallas DOI
15:00 5m Talk		HEJ-Robust: A Robustness Benchmark for LLM-Based Automated Program Repair Benchmark & Dataset Track Fazle Rabbi Concordia University, Jinqiu Yang Concordia University DOI
15:05 5m Paper		JunoBench: A Benchmark Dataset of Crashes in Python Machine Learning Jupyter Notebooks Benchmark & Dataset Track Yiran Wang Linköping University, José Antonio Hernández López Department of Computer Science and Systems, University of Murcia, Ulf Nilsson Linköping University, Daniel Varro Linköping University / McGill University DOI Pre-print
15:10 5m Talk		AgentTelemetry: A Fault Detection Benchmark and Toolkit for LLM Agent Observability Benchmark & Dataset Track Krishna Chaitanya Balusu Independent DOI
15:15 15m Live Q&A		Joint Q&A Benchmark & Dataset Track

	16:00 - 16:45	Poster Session BMain Track at MB 1.210

	16:45 - 17:45	Brainstorming Panel 2: Software Engineering Beyond Code GenerationMain Track at MB 1.210 Chair(s): Weiyi Shang University of Waterloo We are honored to host the following experts for an in-depth discussion and exchange of ideas: Lin Tan (Purdue University and Amazon) Thomas Cottenier (Arm) Rajdeep Mukherjee (Amazon) Baishakhi Ray (Columbia University) Yintong Huo (Singapore Management University)

	17:45 - 18:00	Awards & ClosingMain Track at MB 1.210 Chair(s): Tse-Hsun (Peter) Chen Concordia University, Chao Peng Tencent, Baishakhi Ray Columbia University

Wed 8 Jul
Displayed time zone: Eastern Time (US & Canada) change

10:30 - 12:30	Testing 2FSE Research Papers / FSE Journal-First Paper at MB 1.210 Chair(s): Pengyu Nie University of Waterloo

10:30 20m Talk		SETS: A Simple yet Effective DNN Test Selection Approach FSE Journal-First Paper Jingling Wang Nanjing University, Huayao Wu Nanjing University, Peng Wang Nanjing University, Xintao Niu Nanjing University, Changhai Nie Nanjing University
10:50 20m Talk		MetaSel: A Test Selection Approach for Fine-Tuned DNN Models FSE Journal-First Paper Amin Abbasishahkoo The School of EECS, University of Ottawa, Mahboubeh Dadkhah University of Ottawa, Lionel Briand University of Ottawa, Canada; Lero centre, University of Limerick, Ireland, Dayi Lin Centre for Software Excellence, Huawei Canada
11:10 20m Talk		Can Old Tests do New Tricks for Resolving SWE Issues? FSE Research Papers Yang Chen University of Illinois at Urbana-Champaign, Toufique Ahmed IBM, Reyhaneh Jabbarvand University of Illinois at Urbana-Champaign, Martin Hirzel IBM Research Pre-print
11:30 20m Talk		Empirical Insights of Test Selection Metrics under Multiple Testing Objectives and Distribution Shifts FSE Research Papers Jingyu ZHANG Hong Kong Metropolitan University, Fan Wang City University of Hong Kong, Jacky Keung City University of Hong Kong, Yihan Liao City University of Hong Kong, Yan Xiao Sun Yat-sen University, Lei Ma The University of Tokyo & University of Alberta Pre-print
11:50 20m Talk		Cross-Refactoring-Type Test Program Migration for Refactoring Engines FSE Research Papers Chunhao Dong Beijing Institute of Technology, Yanjie Jiang Tianjin University, Yang Zhang Hebei University of Science and Technology, Yuxia Zhang Beijing Institute of Technology, Hui Liu Beijing Institute of Technology
12:10 20m Talk		Denoising Fault Localization with Test Line Proximity FSE Research Papers Marius Smytzek CISPA Helmholtz Center for Information Security, Andreas Zeller CISPA Helmholtz Center for Information Security DOI Pre-print

14:00 - 15:30	LLM for SE 4FSE Journal-First Paper / FSE Ideas, Visions and Reflections / FSE Research Papers at MB 1.210 Chair(s): Mohamad Kassab Boston University

14:00 20m Talk		Detecting Code-Comment Inconsistencies in Smart Contracts by Combining LLM and Program Analysis FSE Research Papers Jiashuo Zhang Peking University, China, Jiachi Chen Zhejiang University, Ting Zhang Peking University, Yue Li Peking University, Daoyuan Wu Lingnan University, Yanlin Wang Sun Yat-sen University, Jianbo Gao Peking University, Ting Chen University of Electronic Science and Technology of China, Zhong Chen
14:20 20m Talk		Unfulfilled Promises: LLM-Based Detection of OS Compatibility Issues in Infrastructure as Code FSE Research Papers Georgios-Petros Drosos ETH Zurich, Georgios Alexopoulos University of Athens, Thodoris Sotiropoulos ETH Zurich, Dimitris Mitropoulos University of Athens, Zhendong Su ETH Zurich
14:40 10m Talk		DePro: Understanding the Role of LLMs in Debugging Competitive Programming Code FSE Ideas, Visions and Reflections Nabiha Parvez Military Institute of Science And Technology, Tanvin Pallab Military Institute of Science And Technology, Mia Mohammad Imran Missouri University of Science and Technology, Tarannum Shaila Zaman University of Maryland Baltimore County
14:50 20m Talk		A Large-Scale Empirical Evaluation of LLMs for Automated Self-Admitted Technical Debt Repayment FSE Journal-First Paper Mohammad Sadegh Sheikhaei Queen's University, Yuan Tian Queen's University, Kingston, Ontario, Shaowei Wang University of Manitoba, Bowen Xu North Carolina State University
15:10 20m Talk		On the synchronization between Hugging Face pre-trained language models and their upstream GitHub repository FSE Journal-First Paper Adekunle Ajibode Queen's University, Abdul Ali Bangash Lahore University of Management Sciences, Oussama Ben Sghaier Queen's University, Bram Adams Queen's University, Ahmed E. Hassan Queen’s University

	16:00 - 17:00	FSE DebateFSE Debate at MB 1.210 Debate Session: The Future of Software Engineering in the Age of AI

Thu 9 Jul
Displayed time zone: Eastern Time (US & Canada) change

10:30 - 12:30	Testing 3FSE Research Papers / FSE Industry Papers / FSE Tool Demonstrations / FSE Ideas, Visions and Reflections at MB 1.210 Chair(s): Nimmi Weeraddana University of Calgary, Canada

10:30 20m Talk		ACME: Automated Clause Mapping Engine for Testing Emerging Database Systems FSE Research Papers Yuancheng Jiang National University of Singapore, Jianing Wang Shandong University, Chuqi Zhang National University of Singapore, Roland H. C. Yap National University of Singapore, Zhenkai Liang National University of Singapore, Manuel Rigger National University of Singapore DOI Pre-print
10:50 20m Talk		Interrogation Testing of CHC Solvers FSE Research Papers David Kaindlstorfer TU Wien, Austria, Anastasia Isychev TU Wien, Valentin Wüstholz ConsenSys, Maria Christakis TU Wien Pre-print
11:10 20m Talk		RAT: Retrieval-Augmented Testing of Certificate Revocation List Parsers in TLS Implementations FSE Research Papers Chu Chen Qufu Normal University, Qianxin Cheng Qufu Normal University, Pinghong Ren Qufu Normal University, Hairong Yu Qufu Normal University, Cong Tian Xidian University, Zhenhua Duan Xidian University, Xu Lu Xidian University, Bin Yu Xidian University, WenSheng Wang Xidian University, Jin Liu Xi'an University of Technology Pre-print
11:30 10m Talk		Software Testing Beyond Closed Worlds: Open-World Games as an Extreme Case FSE Ideas, Visions and Reflections Yusaku Kato Ritsumeikan University, Norihiro Yoshida Ritsumeikan University, Erina Makihara Ritsumeikan University, Katsuro Inoue Ritsumeikan University Pre-print
11:40 20m Talk		AstraGame: Effective and Efficient VLM Agent Serving for Large-Scale Game Testing in an Industry Setting FSE Industry Papers Yuzhe Guo Peking University, Haochuan Lu Tencent, Mengzhou Wu Peking University, Ting Xiong Tencent Inc., Yuetang Deng Tencent, Dezhi Ran Peking University, Wei Yang UT Dallas, Tao Xie Peking University
12:00 10m Talk		ScalerEval: Automated and Consistent Evaluation Testbed for Auto-scalers in Microservices FSE Tool Demonstrations Shuaiyu Xie School of Computer Science, Wuhan University, China, Yang Luo Wuhan University, Yuzhen Tan Wuhan University, Yunqing Yong Wuhan University, Xiaosong Huang Peking University, Jian Wang Wuhan University, Bing Li Wuhan University
12:10 20m Talk		WalleTruth: Visual-oriented Software Testing for Web3 Wallet Browser Extensions FSE Research Papers Xiaohui Hu Huazhong University of Science and Technology, Ningyu He Hong Kong Polytechnic University, Haoyu Wang Huazhong University of Science and Technology DOI Authorizer link

14:00 - 15:30	LLM for SE 7FSE Industry Papers / FSE Research Papers / FSE Journal-First Paper at MB 1.210 Chair(s): Zhijie Wang Concordia University

14:00 20m Talk		Not All RAGs Are Created Equal: A Component-Wise Empirical Study for Software Engineering Tasks FSE Research Papers Qiang Ke Huazhong University of Science and Technology, Yanjie Zhao Huazhong University of Science and Technology, Hongjin Leng Xiamen University Malaysia, Shengming Zhao Fudan University, Haoyu Wang Huazhong University of Science and Technology Pre-print
14:20 20m Talk		ScanCoder: Leveraging Human Attention Patterns to Enhance LLMs for Code FSE Research Papers Yueke Zhang Vanderbilt University, Yifan Zhang Vanderbilt University, Zihan Fang Vanderbilt University, Greg Trafton Naval Research Laboratory, Daniel Levin Vanderbilt University, Kevin Leach Vanderbilt University, Yu Huang Vanderbilt University
14:40 20m Talk		CodeUltraFeedback: An LLM-as-a-Judge Dataset for Aligning Large Language Models to Coding Preferences FSE Journal-First Paper Martin Weyssow DIRO, Université de Montréal, Aton Kamanda DIRO, Université de Montréal, Xin Zhou Singapore Management University, Singapore, Houari Sahraoui DIRO, Université de Montréal
15:00 20m Talk		Empirical Studies of Parameter Efficient Methods for Large Language Models of Code and Knowledge Transfer to R FSE Journal-First Paper Amirreza Esmaeili University of British Columbia, Iman Saberi University of British Columbia Okanagan, Fatemeh Hendijani Fard University of British Columbia, Okanagan
15:20 10m Talk		AutoChecklist: Automated Checklist Refinement for LLM Judges FSE Industry Papers Mansi Uniyal Microsoft, Mukul Singh Microsoft, Gust Verbruggen Microsoft, Vu Le Microsoft, Sumit Gulwani Microsoft

16:00 - 17:00	ClosingFSE Plenary Events at MB 1.210

16:00 60m Day closing		FSE Closing, SRC, Introduction to FSE 2027 FSE Plenary Events

Mon 6 Jul
Displayed time zone: Eastern Time (US & Canada) change


Room	8:00						30						9:00						30						10:00						30						11:00						30						12:00						30						13:00						30						14:00						30						15:00						30						16:00						30						17:00						30
MB 1.210							Main Track Opening				ArXiv Track + Main Track Coding Agents, Software Testing, and Code Understanding																										Keynotes + Main Track AIware Keynotes Session 1																																				Main Track Trustworthy Code Generation, Reliability, and Engineering of AIware Systems																								Main Track Poster Session A												Main Track Brainstorming Panel 1: Model Capability and the Future of Agent Harnesses

Tue 7 Jul
Displayed time zone: Eastern Time (US & Canada) change


Room	11:00						30						12:00						30						13:00						30						14:00						30						15:00						30						16:00						30						17:00						30
MB 1.210	Keynotes + Main Track AIware Keynotes Session 2												Benchmark & Dataset Track + ArXiv Track + Main Track Benchmarks, Datasets, and Evaluation of AIware																								Benchmark & Dataset Track + Main Track Human Factors, Responsible AIware, and Benchmarks & Datasets																								Main Track Poster Session B									Main Track Brainstorming Panel 2: Software Engineering Beyond Code Generation												Main Track Awards & Closing

Wed 8 Jul
Displayed time zone: Eastern Time (US & Canada) change


Room	10:00						30						11:00						30						12:00						30						13:00						30						14:00						30						15:00						30						16:00						30
MB 1.210							FSE Research Papers + FSE Journal-First Paper Testing 2																																										FSE Journal-First Paper + FSE Ideas, Visions and Reflections + FSE Research Papers LLM for SE 4																								FSE Debate FSE Debate

Thu 9 Jul
Displayed time zone: Eastern Time (US & Canada) change


Room	10:00						30						11:00						30						12:00						30						13:00						30						14:00						30						15:00						30						16:00						30
MB 1.210							FSE Research Papers + FSE Industry Papers + FSE Tool Demonstrations + FSE Ideas, Visions and Reflections Testing 3																																										FSE Industry Papers + FSE Research Papers + FSE Journal-First Paper LLM for SE 7																								FSE Plenary Events Closing

Mon 6 Jul
Displayed time zone: Eastern Time (US & Canada) change


Room	8:00			15			30			45			9:00			15			30			45			10:00			15			30			45			11:00			15			30			45			12:00			15			30			45			13:00			15			30			45			14:00			15			30			45			15:00			15			30			45
MB 1.210											AIware Main Track Collaborator or Assistant? How AI Coding Agents Partition Work across P ... 08:50 - 08:55	AIware Main Track When Code Authors Are Agents: A Large-Scale Study of Human–Agent Collab ... 08:55 - 09:00	AIware Main Track Understanding Conversational Patterns in Multi-agent Programming: A Cas ... 09:00 - 09:05 Wink: Recovering from Misbehaviors in Coding Agents 09:05 - 09:10		AIware Main Track Configuring Agentic AI Coding Tools: An Exploratory Study 09:10 - 09:15	AIware Main TrackAIware Honorable Mention Paper Award Deterministic vs. LLM-Controlled Orchestration for COBOL-to-Python Mode ... 09:15 - 09:20	AIware ArXiv Track Developer Experience with AI Coding Agents: HTTP Behavioral Signatures ... 09:20 - 09:25	AIware Main Track VISOR: A Vision-Language Model-Based Test Oracle for Testing Robots 09:25 - 09:30	AIware Main TrackAIware Honorable Mention Paper Award Fixpad++: Automated Bug Fix Verification using LLM Agents 09:30 - 09:35	AIware Main Track Co-located Tests, Better AI Code: How Test Syntax Structure Affects Fou ... 09:35 - 09:40	AIware Main Track Using Mutation-Analysis to Examine an LLM’s Ability to Summarize Code 09:40 - 09:45	AIware Main TrackAIware Honorable Mention Paper Award Testing AIware Systems: A Software Engineering Survey 09:45 - 09:50	AIware ArXiv Track TestMap: Evidence Infrastructure for Foundation-Model-Assisted Test Gen ... 09:50 - 09:55	AIware ArXiv Track Metamorphic Testing for Clinical ML Models: A Framework Proposal and Pi ... 09:55 - 10:00	AIware Main TrackAIware Honorable Mention Paper Award An Empirical Study of Reasoning Steps in Thinking Code LLMs 10:00 - 10:05	AIware Main Track Can LLMs Really Reason about Code? Studying How Well LLMs Understand th ... 10:05 - 10:10	AIware Main Track How Robustly Do LLMs Understand Execution Semantics? 10:10 - 10:15	AIware ArXiv Track Program-as-Weights: A Programming Paradigm for Fuzzy Functions 10:15 - 10:20	AIware Main Track Joint Q&A 10:20 - 10:30								AIware Keynotes From Chatbots to Colleagues: Steering Code-Driven Agents for End-to-End ... 11:00 - 11:20				AIware Keynotes When Implementation Stops Being the Bottleneck: Design in AI-Native Sof ... 11:20 - 11:40				AIware Keynotes From Features to Data and Domain Knowledge: Reflections on Two Decades ... 11:40 - 12:00				AIware Keynotes Joint Q&A 12:00 - 12:30																								AIware Main Track VeriTrans: Fine-Tuned LLM-Assisted NL→PL Translation via a Deterministi ... 14:00 - 14:05	AIware Main Track Kubernetes Misconfigurations in the Wild: Taxonomy, Evolution, and Auto ... 14:05 - 14:10	AIware Main TrackAIware Honorable Mention Paper Award Quality and Security Signals in AI-Generated Python Refactoring Pull Re ... 14:10 - 14:15 From Assistance to Agency: Rethinking Autonomy and Control in CI/CD Pip ... 14:15 - 14:20		AIware Main Track Beyond Translation Accuracy: Addressing False Failures in LLM-Based Cod ... 14:20 - 14:25	AIware Main Track Executable but Unlearnable: Designing Code That Resists LLM-Based Learning 14:25 - 14:30	AIware Main Track Detecting Unsoundness in Neural Network Verifiers via Concrete–Abstract ... 14:30 - 14:35	AIware Main Track From Correctness to Consistency: Redefining Reliability for the Agentwa ... 14:35 - 14:40	AIware Main Track A Preliminary Study on Explaining Risk of Code Changes using LLM-Based ... 14:40 - 14:45	AIware Main TrackAIware Honorable Mention Paper Award When AI Coding Assistants Leak Training Data: A Study of LLM Memorizati ... 14:45 - 14:50	AIware Main Track Zombie Agents: Detecting Semantic Livelock in Long-Horizon Autonomous S ... 14:50 - 14:55	AIware Main Track Neural-Symbolic Multi-objective Optimization for Performance-Aware ORM ... 14:55 - 15:00	AIware Main Track TriORM: Workload-Aware Neural-Symbolic Multi-objective Optimization for ... 15:00 - 15:05	AIware Main Track Artifact Readiness Gates with Saturation Stop Rules and Host-Parity Adm ... 15:05 - 15:10	AIware Main TrackAIware Honorable Mention Paper Award Towards Migrating Neural Network Implementations 15:10 - 15:15	AIware Main Track From Code Review to Spec-Driven Contracts: A Vision for Auditable AIWar ... 15:15 - 15:20	AIware Main Track Joint Q&A 15:20 - 15:30

Tue 7 Jul
Displayed time zone: Eastern Time (US & Canada) change


Room	11:00			15			30			45			12:00			15			30			45			13:00			15			30			45			14:00			15			30			45			15:00			15			30			45
MB 1.210	AIware Keynotes Formal Methods for Reliable AI Reasoning 11:00 - 11:20				AIware Keynotes Spec-Driven Development for Autonomous Coding Agents Across the SDLC 11:20 - 11:40				AIware Keynotes Joint Q&A 11:40 - 12:00				AIware Benchmark & Dataset Track ClassEval-Pro: A Cross-Domain Benchmark for Class-Level Code Generation 12:00 - 12:05	AIware Benchmark & Dataset Track SWE-Bench+: Enhanced LLM Coding Benchmark 12:05 - 12:10	AIware Benchmark & Dataset Track Do Agents Dream of Root Shells? Partial-Credit Evaluation of LLM Agents ... 12:10 - 12:15	AIware Benchmark & Dataset Track A Dataset of Agentic AI Coding Tool Configurations 12:15 - 12:20	AIware Benchmark & Dataset Track AgenticFlict: A Large-Scale Dataset of Merge Conflicts in AI Coding Age ... 12:20 - 12:25	AIware ArXiv Track TestEvo-Bench: An Executable and Live Benchmark for Test and Code Co-Ev ... 12:25 - 12:30																			AIware Main Track Is Artificial Intelligence an Elixir to the Software Engineering Commun ... 14:00 - 14:05 Towards AI as a Collaborative Partner: A Taxonomy of AI Agent Behavior ... 14:05 - 14:10		AIware Main Track Auditing Who Appears to Belong: A Large-Scale Empirical Study of Bias i ... 14:10 - 14:15	AIware Main Track Operationalizing Ethics for AI Agents: How Developers Encode Values int ... 14:15 - 14:20	AIware Main Track Accountable Agents in Software Engineering: An Analysis of Terms of Ser ... 14:20 - 14:25	AIware Main Track SOSecure: The Wisdom of the Crowd for Safer AI-Generated Code 14:25 - 14:30	AIware Benchmark & Dataset TrackAIware Best Benchmark/Dataset Paper Award SecVulEval: Context-Aware Benchmarking of LLMs for Vulnerability Detection 14:30 - 14:35	AIware Benchmark & Dataset Track SecMutBench: Evaluating LLM-Generated Security Tests via Mutation-Based ... 14:35 - 14:40	AIware Benchmark & Dataset Track CrossCommitVuln-Bench: A Dataset of Multi-commit Python Vulnerabilities ... 14:40 - 14:45	AIware Benchmark & Dataset Track REBench: A Procedural, Fair-by-Construction Benchmark for LLMs on Strip ... 14:45 - 14:50	AIware Benchmark & Dataset Track RustBuildEq: A Benchmark for Binary Equivalence under Build Variability 14:50 - 14:55	AIware Benchmark & Dataset Track TOGBench: A Developer-Written Multi-variant Dataset and Benchmark Suite ... 14:55 - 15:00	AIware Benchmark & Dataset Track HEJ-Robust: A Robustness Benchmark for LLM-Based Automated Program Repair 15:00 - 15:05	AIware Benchmark & Dataset Track JunoBench: A Benchmark Dataset of Crashes in Python Machine Learning Ju ... 15:05 - 15:10	AIware Benchmark & Dataset Track AgentTelemetry: A Fault Detection Benchmark and Toolkit for LLM Agent O ... 15:10 - 15:15	AIware Benchmark & Dataset Track Joint Q&A 15:15 - 15:30

Wed 8 Jul
Displayed time zone: Eastern Time (US & Canada) change


Room	10:00			15			30			45			11:00			15			30			45			12:00			15			30			45			13:00			15			30			45			14:00			15			30			45			15:00			15			30			45
MB 1.210							FSE Journal-First Paper SETS: A Simple yet Effective DNN Test Selection Approach 10:30 - 10:50				FSE Journal-First Paper MetaSel: A Test Selection Approach for Fine-Tuned DNN Models 10:50 - 11:10				FSE Research Papers Can Old Tests do New Tricks for Resolving SWE Issues? 11:10 - 11:30				FSE Research Papers Empirical Insights of Test Selection Metrics under Multiple Testing Obj ... 11:30 - 11:50				FSE Research Papers Cross-Refactoring-Type Test Program Migration for Refactoring Engines 11:50 - 12:10				FSE Research Papers Denoising Fault Localization with Test Line Proximity 12:10 - 12:30																						FSE Research Papers Detecting Code-Comment Inconsistencies in Smart Contracts by Combining ... 14:00 - 14:20				FSE Research Papers Unfulfilled Promises: LLM-Based Detection of OS Compatibility Issues in ... 14:20 - 14:40				FSE Ideas, Visions and Reflections DePro: Understanding the Role of LLMs in Debugging Competitive Programm ... 14:40 - 14:50		FSE Journal-First Paper A Large-Scale Empirical Evaluation of LLMs for Automated Self-Admitted ... 14:50 - 15:10				FSE Journal-First Paper On the synchronization between Hugging Face pre-trained language models ... 15:10 - 15:30

Thu 9 Jul
Displayed time zone: Eastern Time (US & Canada) change


Room	10:00			15			30			45			11:00			15			30			45			12:00			15			30			45			13:00			15			30			45			14:00			15			30			45			15:00			15			30			45			16:00			15			30			45
MB 1.210							FSE Research Papers ACME: Automated Clause Mapping Engine for Testing Emerging Database Systems 10:30 - 10:50				FSE Research Papers Interrogation Testing of CHC Solvers 10:50 - 11:10				FSE Research Papers RAT: Retrieval-Augmented Testing of Certificate Revocation List Parsers ... 11:10 - 11:30				FSE Ideas, Visions and Reflections Software Testing Beyond Closed Worlds: Open-World Games as an Extreme Case 11:30 - 11:40		FSE Industry Papers AstraGame: Effective and Efficient VLM Agent Serving for Large-Scale Ga ... 11:40 - 12:00				FSE Tool Demonstrations ScalerEval: Automated and Consistent Evaluation Testbed for Auto-scaler ... 12:00 - 12:10		FSE Research Papers WalleTruth: Visual-oriented Software Testing for Web3 Wallet Browser Ex ... 12:10 - 12:30																						FSE Research Papers Not All RAGs Are Created Equal: A Component-Wise Empirical Study for So ... 14:00 - 14:20				FSE Research Papers ScanCoder: Leveraging Human Attention Patterns to Enhance LLMs for Code 14:20 - 14:40				FSE Journal-First Paper CodeUltraFeedback: An LLM-as-a-Judge Dataset for Aligning Large Languag ... 14:40 - 15:00				FSE Journal-First Paper Empirical Studies of Parameter Efficient Methods for Large Language Mod ... 15:00 - 15:20				FSE Industry Papers AutoChecklist: Automated Checklist Refinement for LLM Judges 15:20 - 15:30								FSE Plenary Events FSE Closing, SRC, Introduction to FSE 2027 16:00 - 17:00

Room information: MB 1.210

Mon 6 Jul
Displayed time zone: Eastern Time (US & Canada) change

Tue 7 Jul
Displayed time zone: Eastern Time (US & Canada) change

Wed 8 Jul
Displayed time zone: Eastern Time (US & Canada) change

Thu 9 Jul
Displayed time zone: Eastern Time (US & Canada) change

Mon 6 Jul
Displayed time zone: Eastern Time (US & Canada) change

Main Track

ArXiv Track + Main Track

Keynotes + Main Track

Main Track

Main Track

Main Track

Tue 7 Jul
Displayed time zone: Eastern Time (US & Canada) change

Keynotes + Main Track

Benchmark & Dataset Track + ArXiv Track + Main Track

Benchmark & Dataset Track + Main Track

Main Track

Main Track

Main Track

Wed 8 Jul
Displayed time zone: Eastern Time (US & Canada) change

FSE Research Papers + FSE Journal-First Paper

FSE Journal-First Paper + FSE Ideas, Visions and Reflections + FSE Research Papers

FSE Debate

Thu 9 Jul
Displayed time zone: Eastern Time (US & Canada) change

FSE Research Papers + FSE Industry Papers + FSE Tool Demonstrations + FSE Ideas, Visions and Reflections

FSE Industry Papers + FSE Research Papers + FSE Journal-First Paper

FSE Plenary Events

Mon 6 Jul
Displayed time zone: Eastern Time (US & Canada) change

Tue 7 Jul
Displayed time zone: Eastern Time (US & Canada) change

Wed 8 Jul
Displayed time zone: Eastern Time (US & Canada) change

Thu 9 Jul
Displayed time zone: Eastern Time (US & Canada) change

Tracks

Room information: MB 1.210

Program Display Configuration

Mon 6 JulDisplayed time zone: Eastern Time (US & Canada) change

Tue 7 JulDisplayed time zone: Eastern Time (US & Canada) change

Wed 8 JulDisplayed time zone: Eastern Time (US & Canada) change

Thu 9 JulDisplayed time zone: Eastern Time (US & Canada) change

Mon 6 JulDisplayed time zone: Eastern Time (US & Canada) change

Main Track

ArXiv Track + Main Track

Keynotes + Main Track

Main Track

Main Track

Main Track

Tue 7 JulDisplayed time zone: Eastern Time (US & Canada) change

Keynotes + Main Track

Benchmark & Dataset Track + ArXiv Track + Main Track

Benchmark & Dataset Track + Main Track

Main Track

Main Track

Main Track

Wed 8 JulDisplayed time zone: Eastern Time (US & Canada) change

FSE Research Papers + FSE Journal-First Paper

FSE Journal-First Paper + FSE Ideas, Visions and Reflections + FSE Research Papers

FSE Debate

Thu 9 JulDisplayed time zone: Eastern Time (US & Canada) change

FSE Research Papers + FSE Industry Papers + FSE Tool Demonstrations + FSE Ideas, Visions and Reflections

FSE Industry Papers + FSE Research Papers + FSE Journal-First Paper

FSE Plenary Events

Mon 6 JulDisplayed time zone: Eastern Time (US & Canada) change

Tue 7 JulDisplayed time zone: Eastern Time (US & Canada) change

Wed 8 JulDisplayed time zone: Eastern Time (US & Canada) change

Thu 9 JulDisplayed time zone: Eastern Time (US & Canada) change

Mon 6 Jul
Displayed time zone: Eastern Time (US & Canada) change

Tue 7 Jul
Displayed time zone: Eastern Time (US & Canada) change

Wed 8 Jul
Displayed time zone: Eastern Time (US & Canada) change

Thu 9 Jul
Displayed time zone: Eastern Time (US & Canada) change

Mon 6 Jul
Displayed time zone: Eastern Time (US & Canada) change

Tue 7 Jul
Displayed time zone: Eastern Time (US & Canada) change

Wed 8 Jul
Displayed time zone: Eastern Time (US & Canada) change

Thu 9 Jul
Displayed time zone: Eastern Time (US & Canada) change

Mon 6 Jul
Displayed time zone: Eastern Time (US & Canada) change

Tue 7 Jul
Displayed time zone: Eastern Time (US & Canada) change

Wed 8 Jul
Displayed time zone: Eastern Time (US & Canada) change

Thu 9 Jul
Displayed time zone: Eastern Time (US & Canada) change