arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2412.09796cs.CLcs.AI
收藏

AutoPatent:一种面向自动专利生成的多智能体框架

AutoPatent: A Multi-Agent Framework for Automatic Patent Generation

Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences(中国科学院深圳先进技术研究院);Dalian University of Technology(大连理工大学);Southern University of Science and Technology(南方科技大学);The University of New South Wales(新南威尔士大学);Shenzhen University of Advanced Technology(深圳理工大学)

Qiyao Wang, Shiwen Ni, Huaren Liu, Shule Lu, Guhong Chen, Xi Feng, Chi Wei, Qiang Qu, Hamid Alinejad-Rokny, Yuan Lin, Min Yang

AI总结:

针对现有专利处理研究多聚焦短文本任务、难生成完整长专利的问题,提出多智能体框架AutoPatent,结合规划、撰写、审查智能体与PGTree、RRAG技术,在D2P基准上实现了优于更大规模LLM的专利生成效果。

摘要:

随着大语言模型(LLM)能力的持续提升,专利处理领域在自然语言处理社区受到了越来越多的关注。然而,现有研究大多集中在专利分类、专利审查等分类任务,或是专利摘要生成、专利问答等短文本生成任务上。本文提出了一项新颖且实用的任务Draft2Patent(草稿转专利),并构建了对应的D2P基准,要求大语言模型基于初始草稿生成平均长度达17K tokens的完整专利。由于专利具有专业性强、术语规范、篇幅冗长的特点,对大语言模型构成了重大挑战。我们提出了名为AutoPatent的多智能体框架,结合基于大语言模型的规划智能体、撰写智能体与审查智能体,并引入PGTree和RRAG技术,用于生成长篇幅、结构复杂且高质量的完整专利文档。实验结果表明,AutoPatent框架显著提升了多种大语言模型生成完整专利的能力。此外我们发现,仅基于Qwen2.5-7B模型的AutoPatent框架生成的专利,在客观指标和人工评估两方面均优于GPT-4o、Qwen2.5-72B、LLAMA3.1-70B等规模更大、能力更强的大语言模型。论文接收后,我们将在https://github.com/QiYao-Wang/AutoPatent公开数据与代码。

英文摘要:

As the capabilities of Large Language Models (LLMs) continue to advance, the field of patent processing has garnered increased attention within the natural language processing community. However, the majority of research has been concentrated on classification tasks, such as patent categorization and examination, or on short text generation tasks like patent summarization and patent quizzes. In this paper, we introduce a novel and practical task known as Draft2Patent, along with its corresponding D2P benchmark, which challenges LLMs to generate full-length patents averaging 17K tokens based on initial drafts. Patents present a significant challenge to LLMs due to their specialized nature, standardized terminology, and extensive length. We propose a multi-agent framework called AutoPatent which leverages the LLM-based planner agent, writer agents, and examiner agent with PGTree and RRAG to generate lengthy, intricate, and high-quality complete patent documents. The experimental results demonstrate that our AutoPatent framework significantly enhances the ability to generate comprehensive patents across various LLMs. Furthermore, we have discovered that patents generated solely with the AutoPatent framework based on the Qwen2.5-7B model outperform those produced by larger and more powerful LLMs, such as GPT-4o, Qwen2.5-72B, and LLAMA3.1-70B, in both objective metrics and human evaluations. We will make the data and code available upon acceptance at \url{https://github.com/QiYao-Wang/AutoPatent}.

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。

↑