ICSE 2026
Sun 12 - Sat 18 April 2026 Rio de Janeiro, Brazil
ICSE 2026 (series) /

Technical Briefings

Accepted Technical Briefings

Agentic Software Engineering: A Roadmap to Software Engineering 3.0

Presenters: Ahmed E. Hassan, Hao Li, Dayi Lin, Bram Adams, Tse-Hsun (Peter) Chen, Yutaro Kashiwa, Dong Qiu, Haoxiang Zhang, and Miku Watanabe.

Abstract: Software Engineering (SE) is shifting from AI-assisted development (SE 2.0) to Agentic Software Engineering (SE 3.0), where autonomous AI agents act as collaborators. This technical briefing establishes the foundations of a disciplined SE 3.0 practice. We synthesize: (1) a large-scale characterization of agent activity in the wild based on the AIDev dataset, (2) an empirical study of 567 Claude Code pull requests across 157 open-source software projects, and (3) the Structured Agentic Software Engineering (SASE) framework that reframes actors, processes, artifacts, and tools. Attendees will leave with evidence-backed mental models, evaluation patterns for agent-authored PRs, and a practical vocabulary (e.g., agent command environment and agent execution environment) for designing trustworthy human-agent workflows.

Designing Systems with Digital Twins and AI Agents

Presenters: Bedir Tekinerdogan.

Abstract: Digital Twin and AI Agent technologies are emerging as key enablers of intelligent systems across domains such as manufacturing, healthcare, and smart infrastructure. While digital twins provide real-time virtual replicas of physical entities, AI agents extend these models with autonomous decision-making and adaptive capabilities. Architecting such systems requires expertise that spans software architecture, systems engineering, IoT integration, AI engineering, and data science. This brief introduces a systematic approach to building Digital Twin and AI Agent-based systems. It combines a domain-driven method that defines core ontological concepts and relationships between physical, virtual, and agent entities with a design pattern-based approach that addresses challenges of scalability, real-time synchronization, interoperability, and decision automation. Case studies from diverse domains illustrate the practical application of the approach, demonstrating how it enhances system capabilities, optimizes operations, and supports both human and AI-driven decision-making. The goal is to provide a structured framework for architecting next-generation intelligent systems that meet the evolving demands of modern industries.

LLM-Assisted Uncertainty Identification in Self-Adaptive Robotics

Presenters: Hassan Sartaj and Shaukat Ali.

Abstract: Understanding uncertainties present in complex systems, such as self-adaptive robotics, their potential impacts, and mitigation strategies has always been a major challenge for researchers and industry professionals. This hands-on technical briefing will present novel approaches, a tool, and a taxonomy to systematically and automatically identify uncertainty in self-adaptive robotics using large language models (LLMs). The content of this briefing is being developed as part of an EU project named RoboSAPIENS, which aims at ensuring the trustworthiness of self-adaptive robots. To assist industry professionals in the uncertainty identification process, we developed an LLM-based uncertainty identification approach and implemented it in a tool. This briefing will cover LLM-based uncertainty identification, prompting techniques, uncertainty taxonomy, hands-on tool sessions, and experiences from our interactions with industry professionals.

Qualitative Data Analysis and Theory Development

Presenters: Rashina Hoda and Hashini Gunatilake.

Abstract: This technical briefing will enable ICSE attendees to gain hands-on experience with conducting systematic and rigorous qualitative data analysis using socio-technical grounded theory (STGT), and introduce the basics of theory development as an advanced practice in qualitative SE research. It will be useful for students and professional researchers with all levels of experience, including those attempting qualitative research for the first time and those curious about what developing a theory involves. It will equip attendees with the knowledge, skills, and resources required to handle qualitative data from human and LLM sources, and to derive rich descriptive findings, taxonomies, theoretical frameworks, models, and theories.

Quantum Software Engineering 101

Presenters: Shaukat Ali.

Abstract: Quantum Software Engineering (QSE) is an emerging software engineering paradigm that focuses on developing cost-effective quantum software for quantum computers. It is a relatively new area of research, with current studies primarily aimed at designing, developing, testing, and maintaining quantum software. Interest in QSE has been steadily increasing; thus, introducing this topic to the ICSE conference audience will further engage young researchers, senior researchers, and practitioners interested in this area. This technical briefing will begin with an introduction to quantum computing, followed by an overview of QSE. It will then explore QSE in detail from various perspectives, including quantum software requirements engineering, modeling, coding, testing, and debugging. Overall, this technical briefing aims to provide the audience with a comprehensive overview of the current state of QSE as well as future research directions.

Software Engineering for Foundation Models (SE4FM)

Presenters: Boyuan Chen, Dayi Lin, Arthur Leung, Zhilong Chen, Gopi Krishnan Rajbahadur, Gustavo A. Oliva, Yihao Chen, Xiaoshuang Liu, Chun Yong Chong, and Ahmed E. Hassan.

Abstract: Foundation models (FMs) are among humanity’s most complex software systems. They are currently engineered through tribal knowledge and ad‑hoc processes, despite quarterly release cadences and rapidly expanding model size, context length, and modality. This 90‑minute technical briefing presents SE4FM—a disciplined software engineering framing for FMs—organized around four pillars: DataOps (deciding, curating, optimizing, and governing data), ExperimentOps (hypothesis‑driven, scaling‑law‑aware experimentation from small to large; including RLHF/RLAIF/RLVR pipelines), EvalOps (systematic testing, prioritization, and debugging), and FieldOps (releases, monitoring, and compliance). The goal is to give software engineering researchers a unique, insider view of how FMs are really built and run at scale, and to surface concrete SE challenges and opportunities where new SE-centric methods, tools, and theory are urgently needed.

Vibe Engineering: Software Engineering for Software Makers

Presenters: Keheliya Gallaba, Zhiyu Fan, Jiahuei (Justina) Lin, Filipe Cogo, Benjamin Rombaut, Dayi Lin, and Ahmed E. Hassan.

Abstract: “Vibe coding” represents a paradigm shift where non-technical users, or “software makers”, create applications by describing the desired outcome, focusing entirely on the final output rather than the underlying code. This movement, propelled by hyper-growth platforms like Loveable, Bubble, and Glide, actualizes the vision of “AIware” - software for all, by all. However, this remarkable progress is currently confined to applications of limited complexity and introduces significant risks of unreliability and failure. This 90-minute technical briefing introduces SE4SM - a disciplined software engineering framework designed to make vibe coding trustworthy and scalable. SE4SM is built on two foundational pillars: (1) Intent Engineering, which focuses on deeply understanding user needs through multi-agent dialogues, Theory of Mind (ToM) principles, and test-driven requirement refinement; and (2) Realization Engineering, a specialized Agent Execution Environment (AEE) where multi-agent teams autonomously build, test, and verify the software based on the user’s validated intent. This briefing provides an insider’s view of the technical challenges in this domain and surfaces concrete software engineering research opportunities.