MK2 at PBIG Competition: A Prompt Generation Solution
This work addresses the challenge of automated patent-based idea generation for commercial applications, though it is incremental as it builds on existing prompt engineering techniques.
The paper tackled the problem of generating product ideas from patents using a prompt-centric pipeline without extra training data, achieving top performance on an automatic leaderboard and winning 25 out of 36 tests across multiple domains.
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.