Research

Papers

  1. PIPer: On-Device Environment Setup via Online Reinforcement Learning
    Alexander Kovrigin, Aleksandra Eliseeva, Konstantin Grotov, Egor Bogomolov, Yaroslav Zharov
    NeurIPS 2025 Workshop on Deep Learning for Code

    An 8B model trained with SFT and RL from verifiable rewards that matches GPT-4o and Qwen3-32B at environment setup.

  2. EnvBench: A Benchmark for Automated Development Environment Setup
    Aleksandra Eliseeva, Alexander Kovrigin, Ilia Kholkin, Egor Bogomolov, Yaroslav Zharov
    ICLR 2025 Workshop on Deep Learning for Code

    The largest dataset to date for environment setup, with a framework for building and evaluating LLM agents on it.

  3. Long Code Arena: A Set of Benchmarks for Long-Context Code Models
    Egor Bogomolov, Aleksandra Eliseeva, Timur Galimzyanov, Evgeniy Glukhov, Anton Shapkin, Maria Tigina, Yaroslav Golubev, Alexander Kovrigin, Arie van Deursen, Maliheh Izadi, Timofey Bryksin
    arXiv preprint

    Six benchmarks for code models whose context spans a whole repository.

  4. On the Importance of Reasoning for Context Retrieval in Repository-Level Code Editing
    Alexander Kovrigin, Aleksandra Eliseeva, Yaroslav Zharov, Timofey Bryksin
    arXiv preprint

    More deliberate reasoning helps coding agents find the code that matters, though not decide when they have found enough.

  5. Beyond Dynamics: Learning to Discover Conservation Principles
    Antonii Belyshev, Alexander Kovrigin, Andrey Ustyuzhanin
    Machine Learning: Science and Technology

    Representation learning and topology that recover conservation laws from data, including in quantum systems.