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.
Cite
@article{arxiv.2507.08335,
title = {MK2 at PBIG Competition: A Prompt Generation Solution},
author = {Yuzheng Xu and Tosho Hirasawa and Seiya Kawano and Shota Kato and Tadashi Kozuno},
journal= {arXiv preprint arXiv:2507.08335},
year = {2025}
}
Comments
9 pages, to appear in the 2nd Workshop on Agent AI for Scenario Planning (AGENTSCEN 2025)