@inproceedings{cho-etal-2026-supplement,
    title = "Supplement Generation Training for Enhancing Agentic Task Performance",
    author = "Cho, Young Min  and
      Bonadiman, Daniele  and
      Bhargavi, Divya  and
      Alkhouli, Tamer  and
      Romeo, Salvatore  and
      Jiang, Dongwei  and
      Pahwa, Khushbu  and
      Ge, Yubin  and
      Ishii, Etsuko  and
      Sunkara, Monica  and
      Zhang, Yi",
    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.2021/",
    pages = "40662--40675",
    ISBN = "979-8-89176-395-1",
    abstract = "Training large foundation models for agentic tasks is increasingly impractical due to the high computational costs, long iteration cycles, and rapid obsolescence as new models are continuously released. Instead of post-training massive models for every new task or domain, we propose Supplement Generation Training (SGT), a more efficient and sustainable strategy. SGT trains a smaller LLM to generate useful supplemental text that, when appended to the original input, helps the larger LLM solve the task more effectively. These lightweight models can dynamically adapt supplements to task requirements, improving performance without modifying the underlying large models. This approach decouples task-specific optimization from large foundation models and enables more flexible, cost-effective deployment of LLM-powered agents in real-world applications."
}