AutoSpec: An Agentic Framework for Automatically Drafting Patent Specification
On the map: LLM agents and tool use → Web, search, and research agents
Abstract (arXiv)
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.
Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Placed in Web, search, and research agents, one of 16 directions in LLM agents and tool use. Builds on 21 of its 27 references that are in the map. First posted on arXiv 23 Sep 2025.
Builds on
21 of 27 references.
References · 21
- 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
- 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
- 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
- 2015A Diversity-Promoting Objective Function for Neural Conversation Modelscited by 1,077
- 2024PAPILLON: Privacy Preservation from Internet-based and Local Language Model Ensemblescited by 57
- 2024Standardizing the Measurement of Text Diversity: A Tool and a Comparative Analysis of Scorescited by 50
- 2019Patent Claim Generation by Fine-Tuning OpenAI GPT-2cited by 49
- 2024Can Perplexity Reflect Large Language Model's Ability in Long Text Understanding?cited by 45
- 2024Natural Language Processing for the Legal Domain: A Survey of Tasks, Datasets, Models, and Challengescited by 42
- 2023Natural Language Processing in the Legal Domaincited by 38
- 2022The Harvard USPTO Patent Dataset: A Large-Scale, Well-Structured, and Multi-Purpose Corpus of Patent Applicationscited by 33
- 2021PatentSBERTa: A Deep NLP based Hybrid Model for Patent Distance and Classification using Augmented SBERTcited by 24
9 more
- 2024Natural Language Processing in the Patent Domain: A Surveycited by 20
- 2024Can Large Language Models Generate High-quality Patent Claims?cited by 19
- 2023PatFig: Generating Short and Long Captions for Patent Figurescited by 12
- 2025PatentLMM: Large Multimodal Model for Generating Descriptions for Patent Figurescited by 7
- 2023Creating a silver standard for patent simplificationcited by 3
- 2024PatentEval: Understanding Errors in Patent Generationcited by 3
- 2023Attention over pre-trained Sentence Embeddings for Long Document Classificationcited by 2
- 2023Semantic similarity prediction is better than other semantic similarity measurescited by 1
- 2024The Master-Slave Encoder Model for Improving Patent Text Summarization: A New Approach to Combining Specifications and Claimscited by 1
Built on by
Citing papers per year: 2026: 3.
3 papers.
Similar, not cited
Close in wording, no citation either way
- 2024Towards Automated Patent Workflows: AI-Orchestrated Multi-Agent Framework for Intellectual Property Management and Analysis
- 2024AutoPatent: A Multi-Agent Framework for Automatic Patent Generation
- 2025Agent Ideate: A Framework for Product Idea Generation from Patents Using Agentic AI
- 2025ToC: Tree-of-Claims Search with Multi-Agent Language Models
- 2025PATENTWRITER: A Benchmarking Study for Patent Drafting with LLMs
- 2026Vibe Patenting: Evaluating LLM Judges for Professional Patent-Drafting Agents
- 2026IdeaForge: A Knowledge Graph-Grounded Multi-Agent Framework for Cross-Methodology Innovation Analysis and Patent Claim Generation
- 2026QuantumNovelty: A Skill-Orchestrating Language Agent for Referee-Style Review and Patentability Screening of Quantum Papers and Patents