ConferenceGenerative AISimulation
Simulating AI-Human Collaborative Strategies in Sudoku Puzzle Generation
Khalid, M. N. A.
International Conference on Entertainment Computing · pp. 468–477 · 2025
§ sole author
Interactive demo
Generative optimization · puzzle loop
GENERATE→EVALUATE→SEARCH↺
CANDIDATE
GAME REFINEMENT · GR = √G / T
too hardcomfortable 0.07–0.08too easy
waiting for the first candidate…
MAP-ELITES ARCHIVE · click a niche
symmetry →
22 givens← fewer clues · more clues →45
comfortabletoo easytoo hard
0
Puzzles evaluated
0 / 40
Niches filled
0
In comfort zone
DEMO
This interactive is a faithful re-design of the research, simplified for illustrative and teaching purposes. It conveys the idea and behaviour of the model — it is not the paper’s full method, data, or results.
The signature demo: a generator edits Sudoku puzzles, a simulated player computes each one's game-refinement value GR = √G ⁄ T, and a MAP-Elites archive keeps the best puzzle per niche, searching for the comfortable zone 0.07–0.08.
Chicago citation
Khalid, M. N. A. “Simulating AI-Human Collaborative Strategies in Sudoku Puzzle Generation.” In International Conference on Entertainment Computing, 2025.
BibTeX
@inproceedings{khalid2025simulating,
author = {Khalid, M. N. A.},
title = {Simulating AI-Human Collaborative Strategies in Sudoku Puzzle Generation},
booktitle = {International Conference on Entertainment Computing},
pages = {468--477},
year = {2025},
doi = {10.1007/978-3-032-02555-5_35},
}