Legal reasoning requires not only high accuracy but also the ability to justify decisions through verifiable and contestable arguments. However, existing Large Language Model (LLM) approaches, such as Chain-of-Thought (CoT) and Retrieval-Augmented Generation (RAG), often produce unstructured explanations that lack a formal mechanism for verification or user intervention. To address this limitation, we propose Adaptive Collaboration of Argumentative LLMs (ACAL), a neuro-symbolic framework that integrates adaptive multi-agent collaboration with an Arena-based Quantitative Bipolar Argumentation Framework (A-QBAF). ACAL dynamically deploys expert agent teams to construct arguments, employs a clash resolution mechanism to adjudicate conflicting claims, and utilizes uncertainty-aware escalation for borderline cases. Crucially, our framework supports a Human-in-the-Loop (HITL) contestability workflow, enabling users to directly audit and modify the underlying reasoning graph to influence the final judgment. Empirical evaluations on the LegalBench benchmark demonstrate that ACAL outperforms strong baselines across Gemini-2.5-Flash-Lite and Gemini-2.5-Flash architectures, effectively balancing efficient predictive performance with structured transparency and contestability. Our implementation is available at: https://github.com/loc110504/ACAL.

翻译：法律推理不仅要求高准确性，更需要通过可验证且可争议的论证来证成决策。然而，现有的大语言模型方法，如思维链和检索增强生成，通常产生非结构化的解释，缺乏用于验证或用户干预的形式化机制。为应对这一局限，我们提出论辩式大语言模型自适应协作框架，这是一种神经符号框架，它将自适应多智能体协作与基于竞技场的定量双极论证框架相结合。该框架动态部署专家智能体团队以构建论证，采用冲突解决机制裁决相互矛盾的主张，并利用不确定性感知的升级机制处理边界案例。至关重要的是，我们的框架支持人在回路可争议性工作流，使用户能够直接审计并修改底层推理图以影响最终判决。在LegalBench基准上的实证评估表明，该框架在Gemini-2.5-Flash-Lite和Gemini-2.5-Flash架构上均优于强基线模型，有效平衡了高效的预测性能与结构化的透明度及可争议性。我们的实现代码发布于：https://github.com/loc110504/ACAL。