Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

EvoPat: A Multi-LLM-based Patents Summarization and Analysis Agent

Suyuan Wang, Xueqian Yin, Menghao Wang, Ruofeng Guo, Kai Nan

TL;DR

EvoPat tackles the growing complexity of patent information by introducing a multi-agent, multi-LLM analysis pipeline that combines Retrieval-Augmented Generation with structured, cross-patent reasoning. The system preprocesses patent text, embeds it with multilingual capabilities, and analyzes it from five perspectives through specialized agents, while leveraging external data via Google Patents and Semantic Scholar. Empirical results show EvoPat outperforms GPT-4o on standard summarization and evaluation metrics and achieves richer, more extensible analyses, with long-text processing enhanced via Transform Messages and LLMLingua compression. The work demonstrates a scalable approach to patent intelligence and points to future improvements in figure understanding, knowledge graphs, and time-aware trend analysis for even deeper insights.

Abstract

The rapid growth of scientific techniques and knowledge is reflected in the exponential increase in new patents filed annually. While these patents drive innovation, they also present significant burden for researchers and engineers, especially newcomers. To avoid the tedious work of navigating a vast and complex landscape to identify trends and breakthroughs, researchers urgently need efficient tools to summarize, evaluate, and contextualize patents, revealing their innovative contributions and underlying scientific principles.To address this need, we present EvoPat, a multi-LLM-based patent agent designed to assist users in analyzing patents through Retrieval-Augmented Generation (RAG) and advanced search strategies. EvoPat leverages multiple Large Language Models (LLMs), each performing specialized roles such as planning, identifying innovations, and conducting comparative evaluations. The system integrates data from local databases, including patents, literature, product catalogous, and company repositories, and online searches to provide up-to-date insights. The ability to collect information not included in original database automatically is also implemented. Through extensive testing in the natural language processing (NLP) domain, we demonstrate that EvoPat outperforms GPT-4 in tasks such as patent summarization, comparative analysis, and technical evaluation. EvoPat represents a significant step toward creating AI-powered tools that empower researchers and engineers to efficiently navigate the complexities of the patent landscape.

EvoPat: A Multi-LLM-based Patents Summarization and Analysis Agent

TL;DR

EvoPat tackles the growing complexity of patent information by introducing a multi-agent, multi-LLM analysis pipeline that combines Retrieval-Augmented Generation with structured, cross-patent reasoning. The system preprocesses patent text, embeds it with multilingual capabilities, and analyzes it from five perspectives through specialized agents, while leveraging external data via Google Patents and Semantic Scholar. Empirical results show EvoPat outperforms GPT-4o on standard summarization and evaluation metrics and achieves richer, more extensible analyses, with long-text processing enhanced via Transform Messages and LLMLingua compression. The work demonstrates a scalable approach to patent intelligence and points to future improvements in figure understanding, knowledge graphs, and time-aware trend analysis for even deeper insights.

Abstract

The rapid growth of scientific techniques and knowledge is reflected in the exponential increase in new patents filed annually. While these patents drive innovation, they also present significant burden for researchers and engineers, especially newcomers. To avoid the tedious work of navigating a vast and complex landscape to identify trends and breakthroughs, researchers urgently need efficient tools to summarize, evaluate, and contextualize patents, revealing their innovative contributions and underlying scientific principles.To address this need, we present EvoPat, a multi-LLM-based patent agent designed to assist users in analyzing patents through Retrieval-Augmented Generation (RAG) and advanced search strategies. EvoPat leverages multiple Large Language Models (LLMs), each performing specialized roles such as planning, identifying innovations, and conducting comparative evaluations. The system integrates data from local databases, including patents, literature, product catalogous, and company repositories, and online searches to provide up-to-date insights. The ability to collect information not included in original database automatically is also implemented. Through extensive testing in the natural language processing (NLP) domain, we demonstrate that EvoPat outperforms GPT-4 in tasks such as patent summarization, comparative analysis, and technical evaluation. EvoPat represents a significant step toward creating AI-powered tools that empower researchers and engineers to efficiently navigate the complexities of the patent landscape.

Paper Structure

This paper contains 22 sections, 2 figures, 8 tables.

Table of Contents

  1. Introduction
  2. Related work
  3. System Architecture
  4. Overview
  5. Data Preprocessing
  6. Text Extraction
  7. Text Filtering
  8. Text Embedding
  9. Patent Analysis
  10. Long Context Input
  11. Multi-agent System
  12. Tool invoking
  13. Output Integration
  14. Experiments
  15. Experiment Settings
  16. ...and 7 more sections

Figures (2)

  • Figure 1: System overview of EvoPat. For a given patent, the process begins with preprocessing to extract and filter useful information, which is then embedded and stored in a database for easy retrieval in the future. Next, a multi-agent system is employed to analyze the patent from five distinct perspectives. Finally, the results are integrated and outputted as a PDF document for further examination.
  • Figure 2: An example of multi-agent system in EvoPat