| SWE-rebench: An Automated Pipeline for Task Collection and Decontaminated Evaluation of Software Engineering Agents I Badertdinov, A Golubev, M Nekrashevich, A Shevtsov, S Karasik, ... Conference on Neural Information Processing Systems (NeurIPS), 2025, Track …, 2025 | 33 | 2025 |
| Training long-context, multi-turn software engineering agents with reinforcement learning A Golubev, M Trofimova, S Polezhaev, I Badertdinov, M Nekrashevich, ... arXiv preprint arXiv:2508.03501, 2025 | 15 | 2025 |
| Scaling data collection for training software engineering agents I Badertdinov, M Trofimova, Y Anapolskiy, S Abramov, K Zainullina, ... Nebius blog, 2024 | 9 | 2024 |
| Guided Search Strategies in Non-Serializable Environments with Applications to Software Engineering Agents K Zainullina, A Golubev, M Trofimova, S Polezhaev, I Badertdinov, ... International Conference on Machine Learning (ICML), 2025, 2025 | 6 | 2025 |
| Variance reduction for policy-gradient methods via empirical variance minimization M Kaledin, A Golubev, D Belomestny arXiv preprint arXiv:2206.06827, 2022 | 6 | 2022 |
| Leveraging training and search for better software engineering agents. Nebius blog, 2024 A Golubev, S Polezhaev, K Zainullina, M Trofimova, I Badertdinov, ... Nebius blog, 2024 | 3 | 2024 |
| OpenHands Trajectories with Qwen3-Coder-480B-A35B-Instruct M Trofimova, A Shevtsov, I Badertdinov, K Pyaev, S Karasik, A Golubev Nebius blog, 2025 | | 2025 |
Boris YangelHumanoidVerified email at thehumanoid.ai
