AIConfPaper
← Search

Boris Yangel

4 accepted papers

2025

Guided Search Strategies in Non-Serializable Environments with Applications to Software Engineering Agents

Karina Zainullina, Alexander Golubev, Maria Trofimova, Sergei Polezhaev, Ibragim Badertdinov, Daria Litvintseva +6
ICML 2025poster

Large language models (LLMs) have recently achieved remarkable results in complex multi-step tasks, such as mathematical reasoning and agentic software engineering. However, they often struggle to maintain consistent performance across multiple solution attempts. One effective approach to narrow the…

Cited by 0Source ↗PDF ↗Scholar ↗
2025

SWE-rebench: An Automated Pipeline for Task Collection and Decontaminated Evaluation of Software Engineering Agents

Ibragim Badertdinov, Alexander Golubev, Maksim Nekrashevich, Anton Shevtsov, Simon Karasik, Andrei Andriushchenko +3
NeurIPS 2025poster

LLM-based agents have shown promising capabilities in a growing range of software engineering (SWE) tasks. However, advancing this field faces two critical challenges. First, high-quality training data is scarce, especially data that reflects real-world SWE scenarios, where agents must interact with…

Cited by 0Source ↗code ↗Scholar ↗
2021

Shifts: A Dataset of Real Distributional Shift Across Multiple Large-Scale Tasks

Andrey Malinin, Neil Band, Yarin Gal, Mark Gales, Alexander Ganshin, German Chesnokov +10
NeurIPS 2021poster

There has been significant research done on developing methods for improving robustness to distributional shift and uncertainty estimation. In contrast, only limited work has examined developing standard datasets and benchmarks for assessing these approaches. Additionally, most work on uncertainty e…

Cited by 160Source ↗code ↗Scholar ↗
2020

PRANK: motion Prediction based on RANKing

Yuriy Biktairov, Maxim Stebelev, Irina Rudenko, Oleh Shliazhko, Boris Yangel
NeurIPS 2020poster

Predicting the motion of agents such as pedestrians or human-driven vehicles is one of the most critical problems in the autonomous driving domain. The overall safety of driving and the comfort of a passenger directly depend on its successful solution. The motion prediction problem also remains one…

Cited by 34Source ↗PDF ↗Scholar ↗