# Generating Creative Chess Puzzles

arXiv: https://arxiv.org/abs/2510.23881 · HTML: https://mlsanity.com/paper/2510.23881/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Oct 2025.

## Built on by (most cited first, 8 of 8)

- [LongCoT: Benchmarking Long-Horizon Chain-of-Thought Reasoning](https://mlsanity.com/paper/2604.14140/) (2026)
- [Chessformer: A Unified Architecture for Chess Modeling](https://mlsanity.com/paper/2605.19091/) (2026)
- [VAM: Verbalized Action Masking for Controllable Exploration in RL Post-Training -- A Chess Case Study](https://mlsanity.com/paper/2602.16833/) (2026)
- [COrigami: An AI Pipeline for Co-Designing Flat-Foldable Visually Recognisable Origami](https://mlsanity.com/paper/2606.26299/) (2026)
- [Predicting Task Difficulty Without Rollouts](https://mlsanity.com/paper/2608.05797/) (2026)
- [Conditional Generation of Creative Chess Puzzles with Diffusion Models](https://mlsanity.com/paper/2609.38577/) (2026)
- [Benchmarking Prompt Optimization of Large Language Models With Chess](https://mlsanity.com/paper/2610.00416/) (2026)
- [Towards Defining, Measuring, and Leveraging Creativity in AI Applications](https://mlsanity.com/paper/2610.12845/) (2026)

## Abstract (arXiv)

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.