Saved in:
Bibliographic Details
Main Authors: Shea, Ryan, Yu, Zhou
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2509.19640
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914053727715328
author Shea, Ryan
Yu, Zhou
author_facet Shea, Ryan
Yu, Zhou
contents Patents play a critical role in driving technological innovation by granting inventors exclusive rights to their inventions. However the process of drafting a patent application is often expensive and time-consuming, making it a prime candidate for automation. Despite recent advancements in language models, several challenges hinder the development of robust automated patent drafting systems. First, the information within a patent application is highly confidential, which often prevents the use of closed-source LLMs for automating this task. Second, the process of drafting a patent application is difficult for even the most advanced language models due to their long context, technical writing style, and specialized domain knowledge. To address these challenges, we introduce AutoSpec, a secure, agentic framework for Automatically drafting patent Specification. Our approach decomposes the drafting process into a sequence of manageable subtasks, each solvable by smaller, open-source language models enhanced with custom tools tailored for drafting patent specification. To assess our system, we design a novel evaluation protocol in collaboration with experienced patent attorneys. Our automatic and expert evaluations show that AutoSpec outperforms existing baselines on a patent drafting task.
format Preprint
id arxiv_https___arxiv_org_abs_2509_19640
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle AutoSpec: An Agentic Framework for Automatically Drafting Patent Specification
Shea, Ryan
Yu, Zhou
Computation and Language
Patents play a critical role in driving technological innovation by granting inventors exclusive rights to their inventions. However the process of drafting a patent application is often expensive and time-consuming, making it a prime candidate for automation. Despite recent advancements in language models, several challenges hinder the development of robust automated patent drafting systems. First, the information within a patent application is highly confidential, which often prevents the use of closed-source LLMs for automating this task. Second, the process of drafting a patent application is difficult for even the most advanced language models due to their long context, technical writing style, and specialized domain knowledge. To address these challenges, we introduce AutoSpec, a secure, agentic framework for Automatically drafting patent Specification. Our approach decomposes the drafting process into a sequence of manageable subtasks, each solvable by smaller, open-source language models enhanced with custom tools tailored for drafting patent specification. To assess our system, we design a novel evaluation protocol in collaboration with experienced patent attorneys. Our automatic and expert evaluations show that AutoSpec outperforms existing baselines on a patent drafting task.
title AutoSpec: An Agentic Framework for Automatically Drafting Patent Specification
topic Computation and Language
url https://arxiv.org/abs/2509.19640