@inproceedings{li-etal-2026-skill,
    title = "Skill Weaving: Efficient {LLM} Improvement via Modular Skillpacks",
    author = "Li, Zhuo  and
      DU, Guodong  and
      Shi, Zesheng  and
      Guo, Weiyang  and
      Yao, Weijun  and
      Zhou, Yuan  and
      Zhang, Jiabo  and
      Li, Jing",
    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.1989/",
    pages = "40000--40023",
    ISBN = "979-8-89176-395-1",
    abstract = "In this work, we introduce SkillWeave, a modular improvement framework that enables large language models to specialize under fixed memory budgets. SkillWeave partitions full capabilities of a general-purpose model into domain-specific skillpacks{---}lightweight, domain-specific delta modules{---}that reorganize and refine the model{'}s internal knowledge. To ensure deployment efficiency, SkillWeave incorporates SkillZip, a compression component that transforms specialized parameters into lightweight, inference-ready skillpacks. Together, these components allow SkillWeave to achieve strong multi-domain performance and inference-efficient execution. On multi-task and agentic benchmarks, a 9B SkillWeave model outperforms task-specific baselines and even surpasses a 32B monolithic LLM, while achieving up to 4{\texttimes} speedup."
}