KeynotesRequirements Engineering 2026

Language Technology Institute, School of Computer Science, Carnegie Mellon University

Lessons from the Trenches in Building Agents for Software Development

Abstract: Over the past year, AI agents have rapidly developed from a curiosity to a core part of many development workflows. While this development may seem like it was inevitable, it was actually built on a series of rapid technological advances, many built with the assistance of software development agents themselves. In this talk I will talk about several key technologies enabling software-based agents, including the simple but powerful tools developed to provide models with the interfaces that they need, rigorous evaluation benchmarks, and training of agentic models. Further, I will talk about some developing research topics, such as encouraging human-agent interaction, agent memory, and task decomposition.

Bio: Graham Neubig is an associate professor at the Language Technologies Institute of Carnegie Mellon University and Chief Scientist at OpenHands. His research focuses on large language models, including both fundamental advances in model capabilities and applications to tasks such as software development. His final goal is that every person in the world should be able to communicate with each-other, and with computers in their own language. He also contributes to making NLP research more accessible through open publishing of research papers, advanced NLP course materials and video lectures, and open-source software, all of which are available on his website.

University of Stuttgart

Orchestrated Work: AI and the Future of the Workplace

Abstract: The workplace of knowledge workers is heavily changing. Artificial intelligence is not simply augmenting software engineering—it is redefining how work is structured, executed, and governed. Coding is already felt irrelevant by some AI protagonists. Yet, we do not see much productivity improvement, as the very same people now fiddle with copilots and waste time in reworking and polishing their outputs. Most AI is currently introduced ad-hoc without even baselining previous status, nor what are improvements and what are failures. This keynote analyzes implications for the future of work, learning, and expertise. Building on current industry insights from different domains it introduces Orchestrated Work as a unifying paradigm for AI-native organizations. It stimulates industry, research, and education to evolve the workplace and thus envisions a viable position of human knowledge workers in an AI-driven economy.

Bio: Christof Ebert is co-founder and managing director of Vector Consulting Services where he supports companies worldwide on AI, agile transformation and product development. As a business angel, co-founder of Robo-Test incubator and professor at the University of Stuttgart and the Sorbonne in Paris his focus is on building bridges from idea to impact. Getting AI to the workplace has been his focus for three decades, yielding products, patents and industry awards. A Senior Member of the IEEE he serves on editorial boards of IEEE Computer and other leading journals.

Computer Science and Engineering Division, University of Michigan

Revisiting Intelligence Augmentation: Investigating and Mitigating the Risks of AI to Human Intelligence

Abstract: Powerful AI technologies, especially recently developed large language models (LLMs), are increasingly mediating or even replacing human thinking, from information and knowledge acquisition, judgment and decision making, creativity, to our understanding of the world. In 1962, Douglas Engelbart described a vision of Intelligence Augmentation (IA), in which machines should augment, instead of replacing, human thinking. In this talk, I will revisit this vision and pose the question: What are the challenges for achieving IA with increasingly capable and agentic AI? Drawing on human-computer interaction research, including our own work, I will examine two interconnected threats. First, I will present findings from research that studies and mitigates people’s overreliance on AI. I will highlight fundamental obstacles to maintaining human oversight of AI and achieving human-AI complementarity, and argue that a productivity-oriented approach to AI structurally worsens these obstacles. I will then discuss our recent work studying how new affordances of LLMs threaten the integrity of information and knowledge acquisition, and situate this discussion in broader empirical research on how AI is reshaping human cognition. I will close the talk with reflections on what intelligence augmentation actually requires, and how these requirements might be embedded in the technical objectives of AI and the sociotechnical infrastructures through which AI is deployed.

Bio: Q. Vera Liao is an Associate Professor of Computer Science and Engineering at the University of Michigan. Prior to joining U-M in 2025, she worked at Microsoft Research and IBM T.J. Watson Research Center. Her research investigates the risks of emerging AI technologies and mitigates the risks through responsible AI development and human-centered design. She is particularly interested in promoting transparency of AI technologies to ensure human oversight, control, and appropriate trust and reliance. Her work received many paper awards at HCI and AI venues. She currently serves as the co-editor-in-chief for the Springer HCI Book Series and on the Editorial Board of ACM TOCHI and TiiS. She has also served on the organizing committee or as a senior PC member for CHI, CSCW, FaccT, and IUI conferences.