Detecting product price outliers is important for retail and e-commerce stores as erroneous or unexpectedly high prices adversely affect competitiveness, revenue, and consumer trust. Classical techniques offer simple thresholds while ignoring the rich semantic relationships among product attributes. We propose an agentic Large Language Model (LLM) framework that treats outlier price flagging as a reasoning task grounded in related product detection and comparison. The system processes the prices of target products in three stages: (i) relevance classification selects price-relevant similar products using product descriptions and attributes; (ii) relative utility assessment evaluates the target product against each similar product along price influencing dimensions (e.g., brand, size, features); (iii) reasoning-based decision aggregates these justifications into an explainable price outlier judgment. The framework attains over 75% agreement with human auditors on a test dataset, and outperforms zero-shot and retrieval based LLM techniques. Ablation studies show the sensitivity of the method to key hyper-parameters and testify on its flexibility to be applied to cases with different accuracy requirement and auditor agreements.

翻译：检测产品价格异常对于零售和电商企业至关重要，因为错误或异常偏高的价格会严重影响竞争力、营收和消费者信任。传统方法采用简单阈值，却忽略了产品属性间丰富的语义关联。我们提出了一种基于智能体的大语言模型（LLM）框架，将异常价格标记转化为基于相关产品检测与比较的推理任务。该系统通过三个阶段处理目标产品价格：（i）相关性分类——利用产品描述与属性选择价格相关的相似产品；(ii) 相对效用评估——沿价格影响因素维度（如品牌、规格、特性）针对每件相似产品评估目标产品；(iii) 基于推理的决策——将这些论证聚合为可解释的价格异常判断。该框架在测试数据集上与人工审计的一致性超过75%，并优于零样本和基于检索的大语言模型技术。消融实验揭示了该方法对关键超参数的敏感性，并验证了其在不同精度要求和审计一致性场景中应用的灵活性。