Agent Ideate: A Framework for Product Idea Generation from Patents Using Agentic AI
This work addresses the problem of inefficient innovation pipelines for businesses by providing an incremental improvement in automating idea generation from patent data.
The paper tackled the challenge of generating product ideas from patents by developing Agent Ideate, a framework using LLMs and autonomous agents, and found that this agentic approach outperformed standalone LLMs in idea quality, relevance, and novelty across domains like Computer Science and Material Chemistry.
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.