Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Liu, Jiale, Zeng, Yifan, Højmark-Bertelsen, Malte, Gadeberg, Marie Normann, Wang, Huazheng, Wu, Qingyun
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2412.15274
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866912162595733504
author Liu, Jiale
Zeng, Yifan
Højmark-Bertelsen, Malte
Gadeberg, Marie Normann
Wang, Huazheng
Wu, Qingyun
author_facet Liu, Jiale
Zeng, Yifan
Højmark-Bertelsen, Malte
Gadeberg, Marie Normann
Wang, Huazheng
Wu, Qingyun
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2412_15274
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Memory-Augmented Agent Training for Business Document Understanding
Liu, Jiale
Zeng, Yifan
Højmark-Bertelsen, Malte
Gadeberg, Marie Normann
Wang, Huazheng
Wu, Qingyun
Computation and Language
Artificial Intelligence
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.
title Memory-Augmented Agent Training for Business Document Understanding
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2412.15274