Agent Ideate: A Framework for Product Idea Generation from Patents Using Agentic AI

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Kanumolu, Gopichand, Urlana, Ashok, Kumar, Charaka Vinayak, Garlapati, Bala Mallikarjunarao
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916822472720384
author Kanumolu, Gopichand
Urlana, Ashok
Kumar, Charaka Vinayak
Garlapati, Bala Mallikarjunarao
author_facet Kanumolu, Gopichand
Urlana, Ashok
Kumar, Charaka Vinayak
Garlapati, Bala Mallikarjunarao
contents Patents contain rich technical knowledge that can inspire innovative product ideas, yet accessing and interpreting this information remains a challenge. This work explores the use of Large Language Models (LLMs) and autonomous agents to mine and generate product concepts from a given patent. In this work, we design Agent Ideate, a framework for automatically generating product-based business ideas from patents. We experimented with open-source LLMs and agent-based architectures across three domains: Computer Science, Natural Language Processing, and Material Chemistry. Evaluation results show that the agentic approach consistently outperformed standalone LLMs in terms of idea quality, relevance, and novelty. These findings suggest that combining LLMs with agentic workflows can significantly enhance the innovation pipeline by unlocking the untapped potential of business idea generation from patent data.
format Preprint
id arxiv_https___arxiv_org_abs_2507_01717
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Agent Ideate: A Framework for Product Idea Generation from Patents Using Agentic AI
Kanumolu, Gopichand
Urlana, Ashok
Kumar, Charaka Vinayak
Garlapati, Bala Mallikarjunarao
Artificial Intelligence
Information Retrieval
Machine Learning
Multiagent Systems
Patents contain rich technical knowledge that can inspire innovative product ideas, yet accessing and interpreting this information remains a challenge. This work explores the use of Large Language Models (LLMs) and autonomous agents to mine and generate product concepts from a given patent. In this work, we design Agent Ideate, a framework for automatically generating product-based business ideas from patents. We experimented with open-source LLMs and agent-based architectures across three domains: Computer Science, Natural Language Processing, and Material Chemistry. Evaluation results show that the agentic approach consistently outperformed standalone LLMs in terms of idea quality, relevance, and novelty. These findings suggest that combining LLMs with agentic workflows can significantly enhance the innovation pipeline by unlocking the untapped potential of business idea generation from patent data.
title Agent Ideate: A Framework for Product Idea Generation from Patents Using Agentic AI
topic Artificial Intelligence
Information Retrieval
Machine Learning
Multiagent Systems
url https://arxiv.org/abs/2507.01717