用于商业文档理解的记忆增强智能体训练
Memory-Augmented Agent Training for Business Document Understanding
AI总结：
提出Matrix范式，通过经验驱动的记忆优化和迭代学习训练LLM智能体，在商业发票运输参考号提取任务中性能显著提升，API调用更少且成本更低。
摘要：
传统企业在处理商业文档时面临重大挑战，例如从发票中提取运输参考号等任务在物流运营中至关重要，但很大程度上仍依赖人工操作。尽管大型语言模型（LLM）提供了自动化潜力，但将其直接应用于专业商业领域往往效果不佳。我们提出了Matrix（通过推理和迭代探索的记忆增强智能体训练），这是一种新范式，使LLM智能体能够通过经验驱动的记忆优化和迭代学习逐步建立领域专业知识。为验证该方法，我们与全球最大的物流公司之一合作，创建了通用商业语言（Universal Business Language）格式发票文档数据集，专注于运输参考号提取任务。实验表明，Matrix比提示单个LLM的性能高出30.3%，比原始LLM智能体高出35.2%。我们进一步分析了优化系统的指标，发现该智能体系统需要更少的API调用、更低的成本，且平均能分析更长的文档。我们的方法为通过系统性记忆增强将通用LLM转化为专业商业工具处理文档任务确立了新途径。
英文摘要：
Traditional enterprises face significant challenges in processing business documents, where tasks like extracting transport references from invoices remain largely manual despite their crucial role in logistics operations. While Large Language Models offer potential automation, their direct application to specialized business domains often yields unsatisfactory results. We introduce Matrix (Memory-Augmented agent Training through Reasoning and Iterative eXploration), a novel paradigm that enables LLM agents to progressively build domain expertise through experience-driven memory refinement and iterative learning. To validate this approach, we collaborate with one of the world's largest logistics companies to create a dataset of Universal Business Language format invoice documents, focusing on the task of transport reference extraction. Experiments demonstrate that Matrix outperforms prompting a single LLM by 30.3%, vanilla LLM agent by 35.2%. We further analyze the metrics of the optimized systems and observe that the agent system requires less API calls, fewer costs and can analyze longer documents on average. Our methods establish a new approach to transform general-purpose LLMs into specialized business tools through systematic memory enhancement in document processing tasks.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
