# AutoSpec: An Agentic Framework for Automatically Drafting Patent Specification

arXiv: https://arxiv.org/abs/2509.19640 · HTML: https://mlsanity.com/paper/2509.19640/

## 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.

## Placed in

- LLM agents and tool use / [Web, search, and research agents](https://mlsanity.com/agents/web-search-and-research-agents/)

## Builds on (most cited first, 21 of 21)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [A Diversity-Promoting Objective Function for Neural Conversation Models](https://mlsanity.com/paper/1510.03055/) (2015)
- [PAPILLON: Privacy Preservation from Internet-based and Local Language Model Ensembles](https://mlsanity.com/paper/2410.17127/) (2024)
- [Standardizing the Measurement of Text Diversity: A Tool and a Comparative Analysis of Scores](https://mlsanity.com/paper/2403.00553/) (2024)
- [Patent Claim Generation by Fine-Tuning OpenAI GPT-2](https://mlsanity.com/paper/1907.02052/) (2019)
- [Can Perplexity Reflect Large Language Model's Ability in Long Text Understanding?](https://mlsanity.com/paper/2405.06105/) (2024)
- [Natural Language Processing for the Legal Domain: A Survey of Tasks, Datasets, Models, and Challenges](https://mlsanity.com/paper/2410.21306/) (2024)
- [Natural Language Processing in the Legal Domain](https://mlsanity.com/paper/2302.12039/) (2023)
- [The Harvard USPTO Patent Dataset: A Large-Scale, Well-Structured, and Multi-Purpose Corpus of Patent Applications](https://mlsanity.com/paper/2207.04043/) (2022)
- [PatentSBERTa: A Deep NLP based Hybrid Model for Patent Distance and Classification using Augmented SBERT](https://mlsanity.com/paper/2103.11933/) (2021)
- [Natural Language Processing in the Patent Domain: A Survey](https://mlsanity.com/paper/2403.04105/) (2024)
- [Can Large Language Models Generate High-quality Patent Claims?](https://mlsanity.com/paper/2406.19465/) (2024)
- [PatFig: Generating Short and Long Captions for Patent Figures](https://mlsanity.com/paper/2309.08379/) (2023)
- [PatentLMM: Large Multimodal Model for Generating Descriptions for Patent Figures](https://mlsanity.com/paper/2501.15074/) (2025)
- [Creating a silver standard for patent simplification](https://mlsanity.com/paper/2310.15689/) (2023)
- [PatentEval: Understanding Errors in Patent Generation](https://mlsanity.com/paper/2406.06589/) (2024)
- [Attention over pre-trained Sentence Embeddings for Long Document Classification](https://mlsanity.com/paper/2307.09084/) (2023)
- [Semantic similarity prediction is better than other semantic similarity measures](https://mlsanity.com/paper/2309.12697/) (2023)
- [The Master-Slave Encoder Model for Improving Patent Text Summarization: A New Approach to Combining Specifications and Claims](https://mlsanity.com/paper/2411.14072/) (2024)

## Built on by (most cited first, 3 of 3)

- [LLM Agents in Law: Taxonomy, Applications, and Challenges](https://mlsanity.com/paper/2601.06216/) (2026)
- [When Reasoning Hurts Legal Drafting: The Verbalization Bottleneck in Patent Claim Generation](https://mlsanity.com/paper/2607.10480/) (2026)
- [Benchmarking Patent Drafting from Inventor-Style Disclosures](https://mlsanity.com/paper/2608.21249/) (2026)

## 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.