2026 LLM Software Development Winter School

Co-Located with ASE 2026, Munich, Germany

Fri 09 - Sat 10 Oct, 2026
Location: TUM IAS
Email: shengcheng[.]yu[@]tum[.]de
Photo: GenAI

Registration

Registration Open

Registration is now open and will close on 5 September 2026, Anywhere on Earth (AoE).

PhD students, postdoctoral researchers, early-career academic researchers, and industry practitioners are warmly invited to apply. Places are limited, and applications will be reviewed as part of a selection process.

Participation is free of charge. Participants are responsible for covering their own travel and accommodation expenses.

Applications will only be accepted through the registration form. If you have any questions, please contact shengcheng[.]yu[@]tum[.]de.

Register now

About

This winter school focuses on LLM-based software development, combining lectures, hands-on labs, and project-based learning. It introduces how large language models can be applied to software design, automated code generation, testing, usability, security, and privacy. Participants will gain practical skills and conceptual understanding to effectively integrate advanced AI techniques into modern software engineering workflows in both academic and industrial contexts.

The winter school is primarily intended for PhD students, postdoctoral researchers, early-career academic researchers, and industry practitioners working in AI, software engineering, software interaction, and related fields.

It will showcase advanced academic research and cutting-edge industry practices. Participants are therefore expected to have relevant experience or a background in LLM-based software development.

Formal invitation letters will be issued to support applications for travel funding or visas. Beyond issuing the invitation letter, the organizing committee is unable to provide any additional assistance with visa applications.

Winter School Schedule

# Date Time Item
1 09 Oct 9:00 - 12:00 TBA
2 09 Oct 14:00 - 18:00 TBA
3 10 Oct 9:00 - 12:00 TBA
4 10 Oct 14:00 - 18:00 TBA

Organizing Committee

Speakers (Tentative)

More to be announced

Talk by Zhenchang Xing

Title

AI-Native Requirements Engineering: Vision, Principles, and Early Prototype

Abstract

Large language models (LLMs) promise software from a single sentence, but that fluency solves generation, not the harder problem of knowing what to build and when to trust the result. This talk reframes requirements engineering as a second-order control problem: LLMs supply cognitive “energy,” yet compound uncertainty across humans, AI, tools, and organizations. I will present design principles that make unknowns first-class, as well as the conceptualization of requirements space, cognitive-state maps, fog ledgers, and space-aware AI for requirements engineering. Early prototypes will also be presented, showing how human and AI collaboratively drive the exploration, convergence, and validation of requirements. The aim is calibratable trust, not just faster generation.

Bio

Dr. Zhenchang Xing is a Senior Principal Research Scientist and the Science Leader of the Software Systems Group at CSIRO. Dr. Xing’s current research focuses on the interdisciplinary areas of software engineering, human-computer interaction, and responsible AI. He has over 200 peer-reviewed publications in prestigious journals and conferences and has received multiple distinguished paper awards from top-tier software engineering conferences, including the ACM SIGSOFT Distinguished Paper Award, IEEE TCSE Distinguished Paper Award, and ACM SIGSOFT Most Influential Paper Award. Dr. Xing was the Program Co-Chair of ICSME 2020 and will serve as the General Co-Chair of APSEC 2027 and the Program Co-Chair of FSE 2028.

Talk by Jieshan Chen

Title

TBA

Abstract

TBA

Bio

TBA

Talk by Spencer Greene

Title

Building and Deploying Pre-Submit Agentic Program Repair at Google

Abstract

Manual debugging and repair of test failures during continuous integration checks is time-consuming and disruptive to developer flow. While LLMs have advanced automated program repair, existing offline post-submit workflows fail to provide low-latency agentic assistance before developers context switch. In this talk, we introduce FlowAgent, an autonomous AI coding agent deployed across Google to repair pre-submit test failures in continuous integration. We examine FlowAgent's ReAct generate-and-validate architecture and its pre/post-execution abstention filters designed to meet strict industrial latency and trust constraints. We share empirical findings from its Google-wide deployment (including over 26,000 applied fixes) and discuss the open challenges of integrating autonomous coding agents into real-world developer workflows.

Bio

Spencer Greene is a Software Engineer at Google working on AI-powered developer tooling. His work focuses on designing, building, and deploying autonomous AI agents that assist engineers with code review, test debugging, and automated program repair across Google's monorepo. He co-authored recent work on low-latency agentic program repair presented at the ASE 2026 Industry Showcase. For more see https://spencergreene.com/.