@inproceedings{wang-etal-2026-centaurta,
    title = "{C}entaur{TA}: A Self-Improving Human-Agents Collaboration Framework for Thematic Analysis",
    author = "Wang, Lei  and
      Huang, Min  and
      Dragut, Eduard",
    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.778/",
    pages = "15871--15884",
    ISBN = "979-8-89176-395-1",
    abstract = "Qualitative analysis is essential for studying complex social and behavioral phenomena, yet existing large language model (LLM) approaches face key limitations. Fully automated pipelines often compromise methodological rigor, while fully manual coding remains costly and labor-intensive. Although recent work emphasizes human{--}AI collaboration, existing multi-agent systems focus primarily on theme-level outputs, provide limited human oversight, and overlook fine-grained, data-level coding quality.We introduce \textbf{CentaurTA}, an iterative, self-improving human{--}agent framework for scalable thematic analysis. CentaurTA places humans in the loop to oversee and guide analysis, using expert feedback as a persistent learning signal to drive prompt-level refinement. By combining structured human feedback with rubric-based evaluation, CentaurTA provides fine-grained supervision for both open coding and theme construction while preserving methodological rigor. Experiments across multiple datasets, baselines, and LLM families show that CentaurTA improves coding alignment and transparency, highlighting the central role of human feedback in reliable qualitative analysis. Our code and data are available at https://github.com/Tom-Owl/CentaurTA."
}