CAF-Gen: A Multi-Agent System for Enriching Argumentation Structures

CAF-Gen：用于丰富论证结构的多智能体系统

Abstract: Formalizing complex reasoning from natural text is one of the central challenges in computational linguistics. It requires systems to understand not just keywords but also the context and complex reasoning embedded in a text. 摘要： 从自然语言文本中形式化复杂推理是计算语言学面临的核心挑战之一。这要求系统不仅要理解关键词，还要理解文本中蕴含的语境和复杂推理。

Current Argument Mining (AM) techniques identify basic claims and premises, yet they often struggle to capture the richer structural information required by advanced schemas such as the Carneades Argumentation Framework (CAF), which incorporates features such as premise types, proof standards, and argument schemes. 当前的论证挖掘（AM）技术能够识别基本的论点和前提，但往往难以捕捉到高级模式（如 Carneades 论证框架，即 CAF）所要求的更丰富的结构信息，而 CAF 包含了前提类型、证明标准和论证方案等特征。

We address this limitation by introducing CAF-Gen, an automated multi-agent framework designed to enrich shallow argument structures into CAF-compliant argument models. By employing an iterative Creator-Reviewer pipeline, a creator agent’s output is validated by a critical agent to ensure structural integrity. 为了解决这一局限性，我们引入了 CAF-Gen，这是一个自动化的多智能体框架，旨在将浅层的论证结构丰富为符合 CAF 标准的论证模型。通过采用迭代式的“创建者-审查者”（Creator-Reviewer）流水线，创建者智能体的输出会由审查者智能体进行验证，以确保结构的完整性。

This multi-agent collaboration is crucial for mitigating the structural instability typical of single-pass generative models. Our experiments demonstrate that the iterative feedback loop improves the quality of the resulting data and achieves strong alignment with the original annotations, while producing structurally richer models. 这种多智能体协作对于缓解单次生成模型中常见的结构不稳定性至关重要。我们的实验表明，这种迭代反馈循环提高了生成数据的质量，并实现了与原始标注的高度一致，同时产生了结构更丰富的模型。

Our findings show that the multi-agent system can overcome the limitations of single-pass generation, providing a robust methodology for the automated modeling of formal argumentation. 研究结果表明，该多智能体系统能够克服单次生成模型的局限性，为形式化论证的自动建模提供了一种稳健的方法论。