# Fly, Fail, Fix: Iterative Game Repair with Reinforcement Learning and Large Multimodal Models

arXiv: https://arxiv.org/abs/2507.12666 · HTML: https://mlsanity.com/paper/2507.12666/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 28 references that are in the map.
- First posted on arXiv 16 Jul 2025.

## Builds on (most cited first, 19 of 19)

- [Dota 2 with Large Scale Deep Reinforcement Learning](https://mlsanity.com/paper/1912.06680/) (2019)
- [Deep Reinforcement Learning at the Edge of the Statistical Precipice](https://mlsanity.com/paper/2108.13264/) (2021)
- [Eureka: Human-Level Reward Design via Coding Large Language Models](https://mlsanity.com/paper/2310.12931/) (2023)
- [Holodeck: Language Guided Generation of 3D Embodied AI Environments](https://mlsanity.com/paper/2312.09067/) (2023)
- [Reward Design with Language Models](https://mlsanity.com/paper/2303.00001/) (2023)
- [RoboGen: Towards Unleashing Infinite Data for Automated Robot Learning via Generative Simulation](https://mlsanity.com/paper/2311.01455/) (2023)
- [Open-Ended Learning Leads to Generally Capable Agents](https://mlsanity.com/paper/2107.12808/) (2021)
- [Enhanced POET: Open-Ended Reinforcement Learning through Unbounded Invention of Learning Challenges and their Solutions](https://mlsanity.com/paper/2003.08536/) (2020)
- [PCGRL: Procedural Content Generation via Reinforcement Learning](https://mlsanity.com/paper/2001.09212/) (2020)
- [DrEureka: Language Model Guided Sim-To-Real Transfer](https://mlsanity.com/paper/2406.01967/) (2024)
- [Level Generation Through Large Language Models](https://mlsanity.com/paper/2302.05817/) (2023)
- [MarioGPT: Open-Ended Text2Level Generation through Large Language Models](https://mlsanity.com/paper/2302.05981/) (2023)
- [Gen2Sim: Scaling up Robot Learning in Simulation with Generative Models](https://mlsanity.com/paper/2310.18308/) (2023)
- [EnvGen: Generating and Adapting Environments via LLMs for Training Embodied Agents](https://mlsanity.com/paper/2403.12014/) (2024)
- [Adversarial Reinforcement Learning for Procedural Content Generation](https://mlsanity.com/paper/2103.04847/) (2021)
- [MAESTRO: Open-Ended Environment Design for Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2303.03376/) (2023)
- [The Ink Splotch Effect: A Case Study on ChatGPT as a Co-Creative Game Designer](https://mlsanity.com/paper/2403.02454/) (2024)
- [FactorSim: Generative Simulation via Factorized Representation](https://mlsanity.com/paper/2409.17652/) (2024)
- [Automatic Playtesting for Game Parameter Tuning via Active Learning](https://mlsanity.com/paper/1908.01417/) (2019)

## Built on by (most cited first, 1 of 1)

- [PREFER: From Player Experience to Personalized Game Refinement](https://mlsanity.com/paper/2610.19213/) (2026)

## Abstract (arXiv)

Game design hinges on understanding how static rules and content translate into dynamic player behavior - something modern generative systems that inspect only a game's code or assets struggle to capture. We present an automated design iteration framework that closes this gap by pairing a reinforcement learning (RL) agent, which playtests the game, with a large multimodal model (LMM), which revises the game based on what the agent does. In each loop the RL player completes several episodes, producing (i) numerical play metrics and/or (ii) a compact image strip summarising recent video frames. The LMM designer receives a gameplay goal and the current game configuration, analyses the play traces, and edits the configuration to steer future behaviour toward the goal. We demonstrate results that LMMs can reason over behavioral traces supplied by RL agents to iteratively refine game mechanics, pointing toward practical, scalable tools for AI-assisted game design.