Sergey Mechtaev / 谢辽夏

Sergey Mechtaev's Portrait
Email
mechtaev@pku.edu.cn
GitHub
github.com/mechtaev
LinkedIn
sergey-mechtaev-6470aa218
Address
Room 1542, Science Building #1, Peking University, No. 5 Yiheyuan Road, Beijing, 100871, China

Sergey Mechtaev is an Assistant Professor at Peking University. Previously, he obtained a PhD degree from the National University of Singapore, and was a faculty member at University College London. His research aims to automate the development and maintenance of trustworthy software. It has been recognized by prestigious awards, notably, an ACM SIGSOFT Outstanding Dissertation Award and three ACM SIGSOFT Distinguished Paper Awards, and has been deployed in industry, at Bloomberg, and academia, at IIT Kanpur.

CV Research Overview Achievements

Publications

  • Authority Is Not a String: A Capability-Scoped Harness for Prompt-Injection-Resistant Coding Agents

    Dimitrios Stamatios Bouras, Yihan Dai, Sergey Mechtaev

    LMPL@SPLASH 2026

  • Compressing Code Context for LLM-based Issue Resolution

    Haoxiang Jia, Earl T. Barr, Sergey Mechtaev

    ASE 2026 PreprintArtifact

  • Defusing Logic Bombs in Symbolic Execution with LLM-Generated Ghost Code

    Dimitrios Stamatios Bouras, Sergey Mechtaev

    ISSTA 2026 Preprint

  • Reducing Hallucinations in LLM-Generated Code via Semantic Triangulation

    Yihan Dai, Sijie Liang, Haotian Xu, Peichu Xie, Sergey Mechtaev

    OOPSLA 2026 PreprintArtifact

  • Statistical Independence Aware Caching for LLM Workflows

    Yihan Dai, Dimitrios Stamatios Bouras, Haoxiang Jia, Sergey Mechtaev

    LLM4Code@ICSE 2026 PreprintArtifact
View All Google Scholar DBLP

News

14/08/26 A paper on prompt-injection-resistant coding agents has been accepted to LMPL'26. 07/08/26 A paper on assessing correctness of LLM-generated code has been accepted to OOPSLA'26. 25/06/26 A paper on LLM-based symbolic execution has been accepted to ISSTA'26. 18/06/26 A paper on context compression for program repair has been accepted to ASE'26. 03/03/26 HoarePrompt [ICSE'26] received ACM SIGSOFT Distinguished Paper Award.

Talks

May 2026

Quality Assurance in The Era of Natural Language Driven Programming

Nanjing University

Dec 2025

Reducing Hallucinations in LLM-Generated Code via Semantic Triangulation

Zhejiang University

Jun 2025

Quality Assurance in The Era of Natural Language Driven Programming

Shanghai Workshop on Structural AI

Group

  • Haoxiang Jia

    PhD Student

  • Dimitrios Stamatios Bouras

    PhD Student

  • Yihan Dai

    PhD Student

  • Haotian Xu

    PhD Student

  • Sijie Liang

    Master's Student

Service

  • ICSE 2027

    Program committee

  • OOPSLA 2027

    Program committee

  • FSE 2027

    Program committee

  • LMPL@SPLASH 2026

    Program committee

  • ICSE 2026

    Program committee

Teaching