Dmitriy Lukashevskiy

MIRAI

Papers on Lattice

Total citations

Topics

Publication activitypapers/week, last 8 weeks

Research focus

RLHF & Preference Learning (1)Tool Use & Agents (1)World Models & Planning (1)

Frequent co-authors

Zoya Volovikova (1)Nikita Sorokin (1)Aleksandr Panov (1)Alexey Skrynnik (1)

Papers (1)

Apr 22, 2026

MIRAIApr 22, 2026

Self-Guided Plan Extraction for Instruction-Following Tasks with Goal-Conditional Reinforcement Learning

Forget meticulously annotating subtasks – SuperIgor lets language models self-learn to generate and refine instruction-following plans through RL feedback.

Zoya Volovikova, Nikita Sorokin, Dmitriy Lukashevskiy +2

RLHF & Preference Learning Tool Use & Agents World Models & Planning

Search

Dmitriy Lukashevskiy

Publication activitypapers/week, last 8 weeks

Research focus

Frequent co-authors

Papers (1)