An Overview and Discussion on Using Large Language Models for Implementation Generation of Solutions to Open-Ended Problems
It discusses a potential new approach for AI researchers to handle open-ended problem-solving, but it is incremental as it only reviews existing work without presenting novel findings.
The paper explores the potential of Large Language Models (LLMs) to automate implementation generation for open-ended problems, such as problem framing and feature elaboration, by summarizing current methods like prompting and Reinforcement Learning, but does not provide concrete results or numbers.
Large Language Models offer new opportunities to devise automated implementation generation methods that can tackle problem solving activities beyond traditional methods, which require algorithmic specifications and can use only static domain knowledge, like performance metrics and libraries of basic building blocks. Large Language Models could support creating new methods to support problem solving activities for open-ended problems, like problem framing, exploring possible solving approaches, feature elaboration and combination, more advanced implementation assessment, and handling unexpected situations. This report summarized the current work on Large Language Models, including model prompting, Reinforcement Learning, and Retrieval-Augmented Generation. Future research requirements were also discussed.