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

TL;DR

Agent Ideate leverages autonomous agents and large language models to mine patents and generate innovative product ideas, outperforming standalone models in quality, relevance, and novelty across multiple domains.

Contribution

This work introduces a novel agentic framework that combines LLMs with autonomous agents to enhance patent-based product idea generation.

Findings

Agentic approach outperforms standalone LLMs in idea quality

Framework effective across multiple scientific domains

Significant potential for innovation pipeline enhancement

Abstract

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.