@inproceedings{eljadiri-nurbakova-2025-team,
    title = "Team {INSAL}yon2 at {S}em{E}val-2025 Task 10: A Zero-shot Agentic Approach to Text Classification",
    author = "Eljadiri, Mohamed - Nour  and
      Nurbakova, Diana",
    editor = "Rosenthal, Sara  and
      Ros{\'a}, Aiala  and
      Ghosh, Debanjan  and
      Zampieri, Marcos",
    booktitle = "Proceedings of the 19th International Workshop on Semantic Evaluation (SemEval-2025)",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/corrections-2025-08/2025.semeval-1.129/",
    pages = "965--980",
    ISBN = "979-8-89176-273-2",
    abstract = "We present Team INSALyon2{'}s agentic approach to SemEval-2025 Task 10 Subtask 2, which focuses on the multi-label classification of narratives in news articles across five languages. Our system employs a zero-shot architecture where specialized Large Language Model (LLM) agents handle binary classification tasks for individual narrative/subnarrative labels, with a meta-agent aggregating these decisions into final multi-label predictions. Instead of fine-tuning on the dataset, we leverage AutoGen to orchestrate multiple GPT-based agents, each responsible for detecting specific narrative/subnarrative types in a modular framework. This agent-based approach naturally handles the challenge of multi-label classification by enabling parallel decisions across the two-level taxonomy. Experiments on the English subset demonstrate strong performance with our system achieving F1{\_}macro{\_}coarse = 0.513, F1{\_}sample = 0.406, securing third place in the competition. Our findings show that zero-shot agentic approaches can be competitive in complex classification tasks."
}