Introducing PCGRL+, the extended version of Procedural Content Generation via Reinforcement Learning ! By smearle, Julian Togelius and me We updated the open-sourced code to Jax implementation, supporting more customized functions and we want to share some fun facts with you! (1/n)

NYU Tandon NYU Tandon made this nice video, which is eight packed minutes of me explaining what I do and why. Watch if you want a high-level overview of my research program. Also, do I really speak that fast?

Are you working on applying LLMs to games in some way? Well, we have the place you will want to submit your work to, namely our special issues on LLMs and Games in IEEE Transactions on Games. Deadline: December 1.

Can LLMs plan? How and when? Our new contribution to help elucidating this complex question is GameTraversalBenchmark, where LLMs are tested on how well they can navigate generated 2D game environments. Easy for humans, very hard for LLMs, but bigger models do better.

Yesterday, Associate Professor @Togelius (CSE) gave a keynote "Generating Games and Game Environments: Challenges and Opportunities" at AI Business — the most important event for commercially applied AI. #NYUTandonMade

If you're at AAAI and interested in games and/or content generation, go see Tim Merino and Michael Middleton present our paper "Moonshine: Distilling Game Content Generators into Steerable Generative Models" in a few minutes in the Human and AI session! There will also be a

I'm giving a little public talk about AGI, based on my AGI book. Very accessible, no technical knowledge required. We'll start in around 5 minutes, at 1.15 ET. It will be recorded and posted online later.

Remember our work on Word2World, where we generate playable worlds based on stories? Continuing this line of research, we have been working on generating Minecraft environments that tell playable stories. Check it out 👇

Procedural Content Generation for Games is a thriving research field with an amazing methodological diversity (including LLMs, RL, and evolutionary algorithms as well as more problem-specific solutions) but few good benchmarks. Until now! We present... the PCG benchmark!

Game Innovation is a new series of videos explaining advances in AI for games. The first video explores ongoing work by Tim Merino on vector-quantized diffusion in Minecraft, and there are several more videos about NYU Tandon Game Innovation Lab's work upcoming.

Associate Prof Julian Togelius explains to BBC that "In Minecraft world, creating [something] is direct and simple," making it accessible when computers might otherwise hinder building impulses. #NYUTandonMade buff.ly/E4OttOH

What would it mean to build AI systems that generate games that are both novel and interesting? The new video in Anjum Asad's Game Innovation series explores this, and describes the GAVEL system by Graham Todd and others in NYU Tandon Game Innovation Lab as an example. Accessible yet detailed!

🌱 On learning (July, TBD): Yasmin Kafai, Vanessa Noemy Bermudez Julian Togelius Registration link to come Penn GSE UCIEducation NYU Tandon Game Innovation Lab

If you happen to be at #CVPR2025 I'm Nashville, I'll give a keynote at the Computer Vision for Videogames workshop at 10.45 today. Room 210.

We've all seen the barrage of video games generated by LLMs on social media. But can we automate this process, and measure the game-generation capabilities of LLMs in a more systematic way? To this end, we introduce ScriptDoctor, a framework for automatically generating

New paper! We are trying to find out how well LLMs can generate functional and novel games in the PuzzleScript game description language, especially when combined with automated playthrough based on search. This is part of our work to create new types of game design assistants.

If you want to use search or RL for games, you need fast simulation. If you want to test your algorithm on many games (or generate new games), you need a game description language. Ergo: we introduce Ludax, a ⚡⚡⚡ fast!🤯 description language for board games. Try it out!

Can we fix PCG generated well designed but non-functional game level levels?? Evolution based algorithms can help to make it functional. arxiv.org/html/2506.1935…

More new work! We’re looking into automatic repair of game levels, designed either humans or algorithms. Basically, can you get the vibe right and then have evolution make the level work properly as well?

Some of our recent work on diffusion models, led by Anubhav Jain, highlighted by Sony!