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
17 Sep Introduction to the seminar Niels Mündler PDF
08 OctOpenHands: An Open Platform for AI Software Developers as Generalist AgentsTBDICLR 2025Niels
AssertFlip: Reproducing Bugs via Inversion of LLM-Generated Passing TestsTBDarXivNiels
15 OctALE-Bench: A Benchmark for Long-Horizon Objective-Driven Algorithm EngineeringTBDarXivKazuki
SWE-bench Multimodal: Do AI Systems Generalize to Visual Software Domains?TBDICLR 2025Kazuki
22 OctScalable, Validated Code Translation of Entire Projects using Large Language ModelsTBDPLDI 2025Robin
Defeating Prompt Injections by DesignTBDarXivRobin
29 OctType-Constrained Code Generation with Language ModelsTBDPLDI 2025Yuhao
AGENTLESS: Demystifying LLM-based Software Engineering AgentsTBDFSE 2025Yuhao
05 NovSWE-GPT: A Process-Centric Language Model for Automated Software ImprovementTBDISSTA 2025Chenhao
Mystique: Automated Vulnerability Patch Porting with Semantic and Syntactic-Enhanced LLMTBDFSE 2025Chenhao
12 NovPolygon: Symbolic Reasoning for SQL using Conflict-Driven Under-Approximation SearchTBDPLDI 25Zuming
ParSEval: Plan-Aware Test Database Generation for SQL Equivalence EvaluationTBDVLDB 25Zuming
19 NovTop Score on the Wrong Exam: On Benchmarking in Machine Learning for Vulnerability DetectionTBDISSTA 25Yuanyuan
We Have a Package for You! A Comprehensive Analysis of Package Hallucinations by Code Generating LLMsTBDUSENIX Security 25Yuanyuan
26 NovRango: Adaptive Retrieval-Augmented Proving for Automated Software VerificationTBDICSE 2025Zenan
Automated Discovery of Tactic Libraries for Interactive Theorem ProvingTBDOOPSLA 2025Zenan
03 DecCODECRASH: Stress Testing LLM Reasoning under Structural and Semantic PerturbationsTBDarXivKhashayar
Leveraging Large Language Models for Enhancing the Understandability of Generated Unit TestsTBDICSE 2025Khashayar
10 DecCopy-and-Patch Compilation: A Fast Compilation Algorithm for High-Level Languages and BytecodeTBDOOPSLA 2021Cong
Automated Verification of Practical Garbage CollectorsTBDPOPL 2009Cong
17 DecSafe kernel extensions without run-time checkingTBDOSDI '96Hao
TALx86: A realistic typed assembly languageTBD1999 ACM SIGPLANHao