TAG
#procedural-content-generation
0 reviews · 9 essays
Related essays
"It Learned to Solve Without Being Taught To" — A Diffusion Model That Generates Solvable Sokoban Without a Solver
One piece today: the preprint "Solvable Sokoban Without a Solver via Diffusion" (Sina Baghal), posted to arXiv on August 16, 2026. Deciding whether a Sokoban puzzle is solvable is PSPACE-complete, so puzzle generation has traditionally relied on expensively running an actual solver. This paper trains a Transformer-based discrete diffusion model with no access to solvers, rewards, or solvability labels — just the task of filling in masked grid cells — and finds that 77.4% of generated puzzles are directly solvable, with 94.5% of the rest fixable by removing a single wall. It explains the mechanism through generation-order flexibility: a global property (solvability) leaking out of a purely local training objective.
"Simple-Looking, Surprisingly Tough" — Generating Slit Paperfolding Puzzles at FDG 2026
One piece today: "Difficulty-based generation of paperfolding puzzles" by Stiliyan Nanovski, Mrinal Dhume, and Rafael Bidarra (TU Delft, Netherlands), presented at the Procedural Content Generation Workshop co-located with Foundations of Digital Games 2026 (FDG '26), held August 10–13, 2026 in Copenhagen. The paper generalizes an existing square-grid, slit-based paperfolding puzzle into a model supporting arbitrary shapes and slits, and builds a constraint-solving generator that derives folded states for a given paper shape and size. Puzzle difficulty is scored based on the types of folds required, and the generator surfaced new fold types made possible only by the slits. I was unable to load the full PDF due to its file size, so this summary is based on the authors' published abstract.
"When You're Stuck, It Quietly Gets Easier" — Reactive Crossword Construction from FDG 2026
One piece today: "Dynamic Crossword Difficulty via Reactive Puzzle Construction" by Colan Biemer and Seth Cooper (Northeastern University), presented at the Procedural Content Generation Workshop co-located with Foundations of Digital Games 2026 (FDG '26), held August 10–13, 2026 in Copenhagen. Unlike a conventional crossword where every square is fixed before play, this paper proposes and evaluates a "reactive" construction method that quietly lowers difficulty when a solver gets stuck and adds easier intersecting "hint" words. Across simulated Beginner-to-Expert personas, the reactive-with-hints variant produced the largest drops in both solve time and surprisal (a difficulty measure). The authors themselves note the method isn't suited for players who want a genuine challenge.
How do you measure a "good mechanic"? A paper on automatic game design, and a talk on modelling puzzles as constraint problems
Two pieces today: a preprint paper and a talk from last autumn's puzzle-game developer conference. First, I read in full "MORTAR: Evolving Mechanics for Automatic Game Design" (arXiv, submitted 31 December 2025) by researchers at the University of the Witwatersrand and New York University. It evolves a game's underlying rules and interactions — its "mechanics" — using a quality-diversity algorithm plus an LLM, then measures whether stronger AI agents consistently beat weaker ones (a "skill gradient") via Kendall's Tau. Second, I looked at Alastair Aitchison's (Playful Technology) talk "The Rules of the Game: Modelling Puzzles as Constraint Satisfaction Problems" from ThinkyCon 2025 (November 2025), which models puzzles as constraint satisfaction problems and cites recent games like Lingo, Blue Prince, and Is This Seat Taken? Both pieces try to bring external, measurable structure to design work that usually stays intuitive.
Halina & Guzdial: Generating Levels as a "Cake of Time" — Fukai Reads
A procedural level-generation paper by Halina and Guzdial. It represents a level as a "cake" of board states stacked over time, and generates a level and its solution together with PRP, which recombines play traces. In Sokoban, against six existing methods, it reached 100% playability with high diversity, without hand-authored constraints or rewards.
Earle et al.: Recasting Level Design from a One-Person Job to a Multi-Agent Collaboration — Fukai Reads
A paper on reinforcement-learning level generation (PCGRL) by Earle et al. It recasts the traditional single-agent, tile-by-tile method as a multi-agent problem in which several agents divide the work and edit in parallel, showing across maze and dungeon domains that more agents improve generation quality, generalization to unseen boards, and computational efficiency.
Bhaumik et al.: Stitching WFC and Reinforcement Learning for Playable, Good-looking Levels — Fukai Reads
A procedural level generation paper by Bhaumik et al. It tackles the weaknesses of WFC (good-looking but unplayable) and reinforcement learning (playable but ugly) with WCRL, which narrows the RL agent's actions using WFC's local rules, generating Lode Runner levels that are both example-like and playable.
Aryan et al.: When You Stall, the World Changes — AbideGym Turns Static RL Worlds into Adaptivity Tests — Fukai Reads
A preprint by Aryan et al. (Abide AI) on RL environment design. To fight the brittleness that comes from training in fully static worlds, AbideGym rewrites the rules and grows the map mid-episode, triggered by the agent's own inactivity, forcing it to abandon memorized policies and re-plan. The paper presents the design and a comparison to prior work; no experimental results yet.
Jara Gonzalez & Guzdial: Generating Enemy Shapes as Gates You Need a Mechanic to Beat — Fukai Reads
A paper by Jara Gonzalez and Guzdial on generating enemy morphologies (collision shapes). They frame 'enemies defeatable only with a specific mechanic' as a 4x4 grid generation problem, compare reinforcement learning, A* search, and neural generation, and find a simple A* reachability rule yields the best gating and most diverse shapes at the lowest cost.
