MK2 at PBIG Competition: A Prompt Generation Solution

TL;DR

This paper introduces MK2, a prompt-based pipeline that leverages iterative prompt editing and large language models to generate patent-inspired product ideas, achieving top performance in a competitive benchmark.

Contribution

The paper presents MK2, a novel prompt-centric approach combining iterative prompt refinement and model evaluation without extra training data for patent-based idea generation.

Findings

MK2 outperformed competitors on the automatic leaderboard.

The approach won 25 of 36 tests across multiple domains.

Materials chemistry domain showed room for improvement.

Abstract

The Patent-Based Idea Generation task asks systems to turn real patents into product ideas viable within three years. We propose MK2, a prompt-centric pipeline: Gemini 2.5 drafts and iteratively edits a prompt, grafting useful fragments from weaker outputs; GPT-4.1 then uses this prompt to create one idea per patent, and an Elo loop judged by Qwen3-8B selects the best prompt-all without extra training data. Across three domains, two evaluator types, and six criteria, MK2 topped the automatic leaderboard and won 25 of 36 tests. Only the materials-chemistry track lagged, indicating the need for deeper domain grounding; yet, the results show that lightweight prompt engineering has already delivered competitive, commercially relevant ideation from patents.