2 citations · 3 across the 6 of their papers we have counts for
8 papers
Training Advisors for LLM Agents from Task Outcomes
Sergei Polezhaev, Barys Liskavets, Ori Press +1
Large language model agents tackle multi-step tasks by interleaving reasoning and tool calls with observations from the environment. Prior work has shown that natural-language feed…
Blockwise Advantage Estimation for Multi-Objective RL with Verifiable Rewards
Kirill Pavlenko, Alexander Golubev, Simon Karasik +1
Group Relative Policy Optimization (GRPO) assigns a single scalar advantage to all tokens in a completion. For structured generations with explicit segments and objectives, this co…
LK Losses: Direct Acceptance Rate Optimization for Speculative Decoding
Alexander Samarin, Sergei Krutikov, Anton Shevtsov +3
Speculative decoding accelerates autoregressive large language model (LLM) inference by using a lightweight draft model to propose candidate tokens that are then verified in parall…
SWE-rebench V2: Language-Agnostic SWE Task Collection at Scale
Ibragim Badertdinov, Maksim Nekrashevich, Anton Shevtsov +1
Software engineering agents (SWE) are improving rapidly, with recent gains largely driven by reinforcement learning (RL). However, RL training is constrained by the scarcity of lar…
Training Long-Context, Multi-Turn Software Engineering Agents with Reinforcement Learning
Alexander Golubev, Maria Trofimova, Sergei Polezhaev +9
Research on applications of reinforcement learning (RL) to large language models has mostly been focused on single-turn problems, such as mathematical reasoning or single-shot code…
Guided Search Strategies in Non-Serializable Environments with Applications to Software Engineering Agents
Karina Zainullina, Alexander Golubev, Maria Trofimova +9
Large language models (LLMs) have recently achieved remarkable results in complex multi-step tasks, such as mathematical reasoning and agentic software engineering. However, they o…
SWE-rebench: An Automated Pipeline for Task Collection and Decontaminated Evaluation of Software Engineering Agents
Ibragim Badertdinov, Alexander Golubev, Maksim Nekrashevich +6
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-…
Variance Reduction for Policy-Gradient Methods via Empirical Variance Minimization
Maxim Kaledin, Alexander Golubev, Denis Belomestny
Policy-gradient methods in Reinforcement Learning(RL) are very universal and widely applied in practice but their performance suffers from the high variance of the gradient estimat…