Overview

This seminar is an opportunity to become familiar with current research in software engineering and more generally with the methods and challenges of scientific research.

Each student will be asked to study some papers from the recent software engineering literature and review them. This is an exercise in critical review and analysis. Active participation is required (a presentation of a paper as well as participation in discussions).

The aim of this seminar is to introduce students to recent research results in the area of programming languages and software engineering. To accomplish that, students will study and present research papers in the area as well as participate in paper discussions. The papers will span topics in both theory and practice, including papers on program verification, program analysis, testing, programming language design, and development tools.

Schedule

DateTitlePresenterVenueTA
16 Sep Introduction to the seminar Niels PDF PDF
07 OctComputer science achievement and writing skills predict vibe coding proficiencyDario Llarden PrietoCHI2026Theo
Validating JVM Compilers via Maximizing Optimization InteractionsMalte DömerASPLOS24Theo
14 OctAre Humans and LLMs Confused by the Same Code? An Empirical Study on Fixation-Related Potentials and LLM PerplexitySandro DienerICSE 2026Sverrir
How AI assistance impacts the formation of coding skillsLivio HellriglSverrir
21 OctRepairAgent: An Autonomous, LLM-Based Agent for Program RepairBenjamin WerlenICSE 2025Yuhao
AutoCodeRover: Autonomous Program ImprovementTim KrauerISSTA 2024Yuhao
28 OctNL2Repo-Bench: Towards Long-Horizon Repository Generation Evaluation of Coding AgentsSimon HüppinICML 2026Kazuki
ProgramBench: Can Language Models Rebuild Programs From Scratch?Silvan HuberarXiv 2026Kazuki
04 NovExploitGym: Can AI Agents Turn Security Vulnerabilities into Real Attacks?Simon RossetarXiv 2026Chenhao
Vero: Can AI Agents Build Formally Verified Software Repositories?Nathan BöhlerarXiv 2026Chenhao
11 NovSWE-Bench ProMax: Benchmarking Agents on Large-Scale Multilingual Code RefactoringVeit AuckenthalerCOLM 2026Kári
SWE-Pruner: Self-Adaptive Context Pruning for Coding AgentsMauro MüllerarXiv 2026Kári
18 NovWelder: Compositional Liveness Verification of Cluster Control PlanesOlivier MorelSOSP 2026Hao
Scaling symbolic evaluation for automated verification of systems code with ServalJacob GorinevskiSOSP 2019Hao
25 NovMosaic: An Interoperable Compiler for Tensor AlgebraJeremy RauchensteinACM 2023Christopher
Quantum Control Machine: The Limits of Control Flow in Quantum ProgrammingGiovanni Di NunzioarXiv 2024Christopher
02 DecCalibration and Correctness of Language Models for CodeMichael KollerICSE 2025Khashayar
Code-MUE: Measuring Code LLMs' Uncertainty through Execution-based Semantic Interaction GraphsLéonard SchaferISSTA 2026Khashayar
09 DecExploiting Undefined Behavior in C/C++ Programs for Optimization: A Study on the Performance ImpactDaniel PfisterPLDI 2025Cong
SkVM: Revisiting Language VM for Skills across Heterogenous LLMs and HarnessesLukas SchenkerSOSP 2026Cong
16 DecSame Scrutiny, More Time: Eye Tracking Insights into Reviewing LLM-Labelled CodeEdison WangASE 2026Maximilian
Deep Learning-based Code Reviews: A Paradigm Shift or a Double-Edged Sword?Ajidan JegatheeswaranICSE 2025Maximilian