Generating Creative Chess Puzzles
Year: 2025
Type: preprint
Abstract: While Generative AI rapidly advances in various domains, generating truly creative, aesthetic, and counter-intuitive outputs remains a challenge. This paper presents an approach to tackle these difficulties in the domain of chess puzzles. We start by benchmarking Generative AI architectures, and then introduce an RL framework with novel rewards based on chess engine search statistics to overcome some of those shortcomings. The rewards are designed to enhance a puzzle's uniqueness, counter-intuitiveness, diversity, and realism. Our RL approach dramatically increases counter-intuitive puzzle generation by 10x, from 0.22\% (supervised) to 2.5\%, surpassing existing dataset rates (2.1\%) and the best Lichess-trained model (0.4\%). Our puzzles meet novelty and diversity benchmarks, retain aesthetic themes, and are rated by human experts as more creative, enjoyable, and counter-intuitive than composed book puzzles, even approaching classic compositions. Our final outcome is a curated booklet of these AI-generated puzzles, which is acknowledged for creativity by three world-renowned experts.
Source: arXiv (Cornell University)
Authors: Feng, Xidong, Veeriah, Vivek, Chiam, Marcus, Dennis, Michael, Pachauri, Ryan, Tumiel, Thomas, Barbero, Federico, Obando-Ceron, Johan, Shi, Jiaxin, Singh, Satinder, Hou, Shaobo, Tomašev, Nenad, Zahavy, Tom
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W7102392255
Cites:
Cited by:
Related to: