@inproceedings{grecu-etal-2026-argchestrators,
    title = "Argchestrators at {UZH} Shared Task 2026: Efficient Argument Mining in {UN} Resolutions: A Sub-8{B} Pipeline using Agentic Debate and Heuristic Retrieval",
    author = "Grecu, Bogdan Octavian  and
      Quaremba, Gerrit  and
      Black, Elizabeth  and
      Vrande{\v{c}}i{\'c}, Denny  and
      Simperl, Elena  and
      Cocarascu, Oana",
    editor = "Elaraby, Mohamed  and
      Hautli-Janisz, Annette  and
      Romberg, Julia  and
      Musi, Elena  and
      Ruggeri, Federico  and
      Lawrence, John",
    booktitle = "Proceedings of the 13th Workshop on Argument Mining and Reasoning",
    month = jul,
    year = "2026",
    address = "San Diego, California, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.argmining-1.13/",
    pages = "109--115",
    ISBN = "979-8-89176-399-9",
    abstract = "The highly formal and negotiated language of United Nations (UN) resolutions presents unique challenges for argument mining. This paper describes our system submitted to the ArgMining 2026 Shared Task: Reconstructing the Reasoning in United Nations Resolutions. Adhering to the strict constraint of utilising open-weight models with at most 8 billion parameters, we propose a hybrid, compute-efficient architecture powered by Qwen3-8B. For the preambular-operative classification, we implement a set of deterministic rules related to the specificity of UN documents, supplemented by an LLM-based multi-label classifier for thematic dimensions and a directed-graph extraction approach for argumentative relation prediction."
}