AutoSpec: An Agentic Framework for Automatically Drafting Patent Specification
This addresses the expensive and time-consuming process of drafting patent applications for inventors and legal professionals, though it appears incremental as it builds on existing language model advancements.
The authors tackled the problem of automating patent drafting by introducing AutoSpec, a secure agentic framework that decomposes the process into subtasks solvable by open-source language models, and it outperformed existing baselines in evaluations with patent attorneys.
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.