Extracting argument structures from legal-political discourse reveals how policies and actions are proposed, debated, and formalized, but remains challenging due to the complexity of long-form, structured text. This work proposes a modular, retrieval-augmented system for traceable and structured argument mining in long, bilingual United Nations resolutions. This paper describes our system submission to the UZH Shared Task 2026, focusing on practical design choices for argument structure modeling under task and model constraints. Our system employs a parameter-efficient (≤8B) open-source model, Qwen3:8B in thinking mode, to perform paragraph classification, multi-label tag assignment, and multi-label relation prediction through a modular, retrieval-augmented pipeline. Our approach integrates retrieval augmentation with self-consistency and self-refinement to address challenges related to scale, no supervision, structured reasoning, and output stability. Experiments on the dataset show that retrieval augmentation improves tag assignment precision, while iterative prompting enhances consistency in output prediction across documents of varying length. The code has been made publicly available.