用三模型对抗评审提升技术文档生成质量，尤其在安全与代码上效果显著。
TriAdReview: Triangular Adversarial Review Architecture for Multi-Model Technical Document Generation
- 构建双评审+三角评判的对抗架构，分别从工程与边界视角审查生成内容。
- 三模型配置整体提升10.1%，安全审计提升27.6%，代码生成提升20.8%。
- 适合需严谨性任务，但对完整性要求高的需求分析有负面影响。
大型语言模型广泛用于技术文档生成，但单模型输出常存在过度设计、安全盲点和覆盖不全问题。本文提出TriAdReview，一种三角对抗评审架构，包含两个独立评审模型（工程视角与边界视角）及三角评判机制，通过迭代优化生成模型输出。我们在五个基准任务——架构设计、代码生成、提案评审、安全审计和需求分析——上评估三种配置：单模型（基线）、双模型（单评审）和三模型（完整系统）。共75次实验（每组n=5）显示，三模型配置相较单模型基线总体提升10.1%（26.2 vs. 23.8/50；p<0.05，配对t检验），在安全审计（+27.6%）、代码生成（+20.8%）和架构设计（+15.6%）上表现突出。另一评分器mimo-v2.5-pro确认趋势但效应较小（+2.7%），表明评分者间一致性中等。然而，需求分析任务出现-7.5%退化，揭示对抗评审架构存在简化倾向，不利于完整性导向任务。通过任务类型框架分析该边界条件，并证明评审提示适配可部分缓解问题。研究首次实证刻画了多模型对抗评审在何种场景下有益或有害，为协同AI系统设计提供依据。
原文摘要 · Abstract (English)
Large language models (LLMs) are increasingly used for technical document generation, yet single-model outputs often suffer from over-engineering, security blind spots, and incomplete coverage. We propose TriAdReview, a triangular adversarial review architecture that employs two independent reviewer models (engineering and boundary perspectives) and a triangular judging mechanism to iteratively improve a generator model's output. We evaluate TriAdReview across five benchmark tasks - architecture design, code generation, proposal review, security audit, and requirements analysis - using three configurations: single model (baseline), dual model (single review), and triple model (full system). Results across 75 experiments (n=5 per cell) show that the triple model configuration achieves a 10.1% overall improvement over the single model baseline (26.2 vs. 23.8 out of 50; p<0.05, paired t-test), with particularly strong gains on security audit (+27.6%), code generation (+20.8%), and architecture design (+15.6%). A second scorer (mimo-v2.5-pro) confirms the direction with a smaller effect (+2.7%), suggesting moderate inter-rater agreement. However, the system shows a -7.5% degradation on requirements analysis, revealing that adversarial review architectures have a structural bias toward simplification that is counterproductive for completeness-oriented tasks. We analyze this boundary condition through a task-type framework and demonstrate that reviewer prompt adaptation partially mitigates the issue. Our findings provide the first empirical characterization of when multi-model adversarial review helps versus harms, with implications for the design of collaborative AI systems.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。