@inproceedings{ren-etal-2026-instructions,
    title = "Instructions are all you need: Self-supervised Reinforcement Learning for Instruction Following",
    author = "Ren, Qingyu  and
      He, Qianyu  and
      Chang, Powei  and
      Zeng, Jie  and
      Sun, Zeye  and
      Yu, Fei  and
      Liang, Jiaqing  and
      Xiao, Yanghua",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.acl-long.217/",
    pages = "4755--4776",
    ISBN = "979-8-89176-390-6",
    abstract = "Language models often struggle to follow multi-constraint instructions that are crucial for real-world applications. Existing reinforcement learning (RL) approaches suffer from dependency on external supervision and sparse reward signals from multi-constraint tasks. We propose a label-free self-supervised RL framework that eliminates dependency on external supervision by deriving reward signals directly from instructions and generating pseudo-labels for reward model training. Our approach introduces constraint decomposition strategies and efficient constraint-wise binary classification to address sparse reward challenges while maintaining computational efficiency. Experiments show that our approach generalizes well, achieving strong improvements across 3 in-domain and 5 out-of-domain datasets, including challenging agentic and multi-turn instruction following. We will open-source our code and data to facilitate future research."
}