通过记忆增强让大模型学会自动提取发票运输信息，效率远超直接使用。
Memory-Augmented Agent Training for Business Document Understanding
- 用迭代学习和记忆更新让大模型逐步积累业务经验
- 在真实物流数据上比单次提示提升30.3%，比普通代理高35.2%
- 更省计算资源，能处理更长文档，适合企业级文档处理
传统企业处理商业文档仍面临巨大挑战，如从发票中提取运输参考信息等关键任务仍依赖人工。尽管大语言模型具备自动化潜力，但其在专业业务领域直接应用效果不佳。我们提出Matrix（基于推理与迭代探索的记忆增强型代理训练），使LLM代理通过经验驱动的记忆优化和迭代学习逐步建立领域专长。为验证该方法，我们与全球最大的物流企业合作，构建了通用业务语言格式的发票数据集，聚焦运输参考提取任务。实验表明，Matrix相比直接提示单一LLM提升30.3%，相比基础LLM代理提升35.2%。进一步分析显示，优化后的系统调用API次数更少、成本更低，平均可处理更长文档。本方法为通过系统性记忆增强，将通用大模型转化为专用业务工具提供了新路径。
原文摘要 · Abstract (English)
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.
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。