Fly, Fail, Fix: Iterative Game Repair with Reinforcement Learning and Large Multimodal Models
This work addresses the challenge of translating static game rules into dynamic player behavior for AI-assisted game design, representing an incremental advancement in automated design tools.
The authors tackled the problem of automated game design iteration by pairing a reinforcement learning agent for playtesting with a large multimodal model to revise game configurations based on behavioral traces, demonstrating that this framework can iteratively refine game mechanics toward specified goals.
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.