LLMs for Code

We study large language models as tools for coding and software development. We focus on the issues of constrained decoding and secure code generation, approaching the latter from the perspectives of evaluation, adversarial attacks that elicit insecure code generations, and developing methods to improve this capability.

Startups and Blog Posts

LogicStar

LogicStar develops autonomous AI for software engineering.

Coding Agents Are "Fixing" Correct Code

Coding agents fail to recognize already-correct code.

Publications

2026

SecPI: Secure Code Generation with Reasoning Models via Security Reasoning Internalization

Hao Wang, Niels Mündler, Mark Vero, Jingxuan He, Dawn Song, Martin Vechev

arXiv 2026

Paper
Code

Constrained Decoding of Diffusion LLMs with Context-Free Grammars

Niels Mündler, Jasper Dekoninck, Martin Vechev

ICLR 2026 DL4C @ NeurIPS'25 Oral

Talk
Website
Paper
Code

Evaluating AGENTS.md: Are Repository-Level Context Files Helpful for Coding Agents?

Thibaud Gloaguen, Niels Mündler, Mark Niklas Müller, Veselin Raychev, Martin Vechev

MemAgents @ ICLR 2026 Oral

Paper
Code

CodeTaste: Can LLMs Generate Human-Level Code Refactorings?

Alex Thillen, Niels Mündler, Veselin Raychev, Martin Vechev

arXiv 2026

Website
Paper
Code

2025

AutoBaxBuilder: Bootstrapping Code Security Benchmarking

Tobias von Arx, Niels Mündler, Mark Vero, Maximilian Baader, Martin Vechev

arXiv 2025

Paper
Code

BaxBench: Can LLMs Generate Secure and Correct Backends?

Mark Vero, Niels Mündler, Victor Chibotaru, Veselin Raychev, Maximilian Baader, Nikola Jovanović, Jingxuan He, Martin Vechev

ICML 2025 Spotlight

Website
Paper
Code

Black-Box Adversarial Attacks on LLM-Based Code Completion

Slobodan Jenko*, Niels Mündler*, Jingxuan He, Mark Vero, Martin Vechev

ICML 2025 * Equal contribution

Paper

Type-Constrained Code Generation with Language Models

Niels Mündler^†, Jingxuan He^†, Hao Wang, Koushik Sen, Dawn Song, Martin Vechev

PLDI 2025 † Co-leadership

Slides
Talk
Paper
Code

Automated Benchmark Generation for Repository-Level Coding Tasks

Konstantinos Vergopoulos*, Mark Niklas Müller*, Martin Vechev

ICML 2025 * Equal contribution

Paper
Code

2024

SWT-Bench: Testing and Validating Real-World Bug-Fixes with Code Agents

Niels Mündler, Mark Niklas Müller, Jingxuan He, Martin Vechev

NeurIPS 2024

Talk
Website
Paper
Code

Instruction Tuning for Secure Code Generation

Jingxuan He*, Mark Vero*, Gabriela Krasnopolska, Martin Vechev

ICML 2024 * Equal contribution

Paper
Code

2023

Large Language Models for Code: Security Hardening and Adversarial Testing

Jingxuan He, Martin Vechev

ACM CCS 2023 Distinguished Paper Award

Slides
Paper
Code