@inproceedings{volovikova-etal-2026-self,
    title = "Self-Guided Plan Extraction for Instruction-Following Tasks with Goal-Conditional Reinforcement Learning",
    author = "Volovikova, Zoya  and
      Sorokin, Nikita  and
      Lukashevskiy, Dmitriy  and
      Panov, Aleksandr  and
      Skrynnik, Alexey",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.findings-acl.1691/",
    pages = "33863--33882",
    ISBN = "979-8-89176-395-1",
    abstract = "We introduce SuperIgor, a framework for instruction-following tasks. Unlike prior methods that rely on predefined subtasks, SuperIgor enables a language model to generate and refine high-level plans through a self-learning mechanism, reducing the need for manual dataset annotation. Our approach involves iterative co-training: an RL agent is trained to follow the generated plans, while the language model adapts and modifies these plans based on RL feedback and preferences. This creates a feedback loop where both the agent and the planner improve jointly. We validate our framework in environments with rich dynamics and stochasticity. Results show that SuperIgor agents adhere to instructions more strictly than baseline methods, while also demonstrating strong generalization to previously unseen instructions."
}