三种AI代理架构对比，多智能体协作提升关系分类效果。
Comparative Analysis of AI Agent Architectures for Entity Relationship Classification
- 设计三种基于大模型的智能体架构，支持自省、分层任务与动态示例生成。
- 多智能体协同在多领域表现接近微调模型，优于标准少样本提示。
- 适合需要高泛化性的结构化信息抽取系统设计参考。
实体关系分类在信息抽取中仍具挑战性，尤其在标注数据有限和关系结构复杂的情况下。本文对三种基于大语言模型（LLMs）的AI代理架构进行对比分析，包括：(1) 反思式自我评估，(2) 分层任务分解，以及(3) 一种新颖的多智能体动态示例生成机制，各自采用不同的推理与提示适应方式。其中，动态示例生成引入实时协作与对抗性提示。我们在多个领域和模型后端上系统比较其性能，结果表明多智能体协调始终优于标准少样本提示，并接近微调模型的表现。研究为构建模块化、可泛化的基于大模型的结构化关系抽取系统提供了实用指导。代码与数据集见https://github.com/maryambrj/ALIEN.git。
原文摘要 · Abstract (English)
Entity relationship classification remains a challenging task in information extraction, especially in scenarios with limited labeled data and complex relational structures. In this study, we conduct a comparative analysis of three distinct AI agent architectures designed to perform relation classification using large language models (LLMs). The agentic architectures explored include (1) reflective self-evaluation, (2) hierarchical task decomposition, and (3) a novel multi-agent dynamic example generation mechanism, each leveraging different modes of reasoning and prompt adaptation. In particular, our dynamic example generation approach introduces real-time cooperative and adversarial prompting. We systematically compare their performance across multiple domains and model backends. Our experiments demonstrate that multi-agent coordination consistently outperforms standard few-shot prompting and approaches the performance of fine-tuned models. These findings offer practical guidance for the design of modular, generalizable LLM-based systems for structured relation extraction. The source codes and dataset are available at https://github.com/maryambrj/ALIEN.git.
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。