Workshop Schedule
Date: July 5, 2026
Venue: Co-located with ACM FSE 2026, Montreal, Canada
Room: MB 3.445, Concordia SGW Campus (Downtown Montreal)
Presentation Timing. Long papers: 8 minutes presentation + 2 minutes Q&A. Short papers: 6 minutes presentation + 2 minutes Q&A. Session chairs will keep time to ensure that all presentations stay on schedule.
| 14:00–14:05 | Opening and Introductions |
| 14:05–14:55 |
Keynote Baishakhi Ray Associate Professor, Columbia University; Amazon Scholar The Next Era of Software Engineering: From Writing Code to Engineering Trust Abstract. Software engineering has always evolved by making software creation easier, from high-level programming languages and integrated development environments to cloud computing and DevOps. Today, generative AI is accelerating this trend dramatically. As AI software engineers become increasingly capable, writing code is rapidly becoming one of the least expensive parts of software development. This changes the fundamental bottleneck of our field. The central challenge is no longer producing software, but establishing confidence that software behaves correctly, securely, and consistently with human intent. Future software engineering will increasingly focus on engineering trust: understanding legacy systems, inferring specifications, verifying AI-generated changes, enforcing security and compliance, and enabling humans and AI agents to collaborate safely on mission-critical software. In this keynote, I will argue that software engineering is entering a new era where verification, behavioral reasoning, executable knowledge, and trustworthy human–AI collaboration become first-class engineering activities. Rather than asking how AI can write more code, we should ask a more fundamental question: How do we build software systems, and AI software engineers, that organizations can truly trust? |
| 15:00–15:30 |
Paper Session I 15:00–15:10 LLM-Based Grid-World Path Planning With Probabilistic Model Checking Asher Tempest Arya, Aren A. Balbikian, Sophia Jit, Marsha Chechik (University of Toronto) 15:10–15:20 Fairness in Multi-Agent Systems for Software Engineering: An SDLC-Oriented Rapid Review Corey Yang-Smith, Ronnie de Souza Santos, Ahmad Abdellatif (University of Calgary) 15:20–15:28 Tone Perturbations as Trust Probes: Evaluating Behavioral Stability of LLMs in Software Engineering Tasks Mohamad Kassab (Boston University); Youssab Ibrahim (New York University Abu Dhabi) 15:28–15:30 · Buffer Transition / brief discussion |
| 15:30–16:00 | Coffee Break |
| 16:00–16:35 |
Paper Session II 16:00–16:10 Latent Security Threats in Modern Software Code Logs Rrezarta Krasniqi, Abanti Chakraborty Shruti (University of North Carolina at Charlotte) 16:10–16:20 A Differential Fuzzing-Based Evaluation of Functional Equivalence in LLM-Generated Code Refactorings Simantika Bhattacharjee Dristi, Matthew B. Dwyer (University of Virginia) 16:20–16:28 LLMSafeGuard: A Training-Free Framework for Safeguarding LLM Decoding via Context-Wise Similarity Validation Ximing Dong (Centre for Software Excellence, Huawei Canada); Shaowei Wang (University of Manitoba); Dayi Lin (Centre for Software Excellence, Huawei Canada); Ahmed E. Hassan (Queen's University) 16:28–16:35 · Discussion Session discussion / transition to invited talks and panel |
| 16:35–17:25 |
Panel and Breakout Discussion Panelists:
|
| 17:25–17:30 | Closing Remarks |