@inproceedings{tang-zhao-2026-smartad,
    title = "{S}mart{AD}: Capacity-Aligned Agent Distillation for Small Language Models",
    author = "Tang, Guokai  and
      Zhao, Feng",
    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.1349/",
    pages = "27045--27057",
    ISBN = "979-8-89176-395-1",
    abstract = "Large language models (LLMs) show strong reasoning and decision-making ability, but their high inference cost motivates transferring agentic skills to small language models (SLMs). Agent distillation trains SLMs on full reason{--}act{--}observe trajectories from a tool-using teacher, enabling SLMs to acquire the tool-use capabilities of large teacher models. However, some teacher-agent trajectories are simply hard for the student to learn, and their compatibility with the student can vary widely; moreover, a uniform token-level loss prevents SLMs from learning the tool-use patterns and final decisions that truly drive successful reasoning. Therefore, we propose SmartAD, a capacity-aligned agent distillation framework that improves both the distilled data and the supervision signal. SmartAD (i) selects, for each training example, the trajectory with the minimum negative log-likelihood among multiple correct teacher samples to obtain student-friendly training data, and (ii) applies a segment-weighted loss that emphasizes action execution and final decision spans over intermediate reasoning. Experiments on multi-hop QA and math benchmarks with 1.5B and 3B models show that SmartAD consistently outperforms all baselines. Overall, our method enables small models to learn the teacher{'}s capabilities more easily and efficiently through trajectory selection and segment-weighted supervision, achieving capacity-aligned distillation."
}