Saved in:
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2605.28258 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918527625068544 |
|---|---|
| author | Huang, Yixu Li, Bo Li, Na Wang, Zhe Chen, Kaijie Ge, Haonan Si, Qingyi Shen, Yuanzhe Yang, Ruihan Wang, Guangjing Guo, Hongcheng |
| author_facet | Huang, Yixu Li, Bo Li, Na Wang, Zhe Chen, Kaijie Ge, Haonan Si, Qingyi Shen, Yuanzhe Yang, Ruihan Wang, Guangjing Guo, Hongcheng |
| contents | Generating a game is not the same as making one that can be played. Despite advances in code generation, existing approaches treat game generation as one-shot translation from prompt to artifact, leaving interaction-level failures undetected. We argue that evaluating and improving game generation requires a player, and study two roles for graphical user interface (GUI) agents in this process: (1) as an objective evaluator, for which we introduce PlaytestArena, a new evaluation environment that pairs 200 browser-based game generation tasks across eight genres with rubrics of expected in-play behaviors, adjudicated by a GUI agent that loads each build in a browser and plays it; and (2) as a subjective playtester, for which we propose Play2Code, where a game agent and a GUI agent operate in a sustained loop with shared memory, turning game generation into a dialogue between coding and playing. Our experiments show that even frontier models struggle to generate playable games directly, while Play2Code achieves a 66.8\% rubric pass-rate, improving over single-pass and agentic-coding baselines by 37.1 and 14.6 points respectively. Further analysis shows that GUI playtester feedback is more traceable than a human report, yet idiosyncratic in ways reminiscent of human testers, establishing game playtesting as a critical testbed for interactive code generation. Our project website is available at https://continual-game-generation.vercel.app/. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_28258 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | GUI Agents for Continual Game Generation Huang, Yixu Li, Bo Li, Na Wang, Zhe Chen, Kaijie Ge, Haonan Si, Qingyi Shen, Yuanzhe Yang, Ruihan Wang, Guangjing Guo, Hongcheng Software Engineering Artificial Intelligence Computer Vision and Pattern Recognition Human-Computer Interaction Generating a game is not the same as making one that can be played. Despite advances in code generation, existing approaches treat game generation as one-shot translation from prompt to artifact, leaving interaction-level failures undetected. We argue that evaluating and improving game generation requires a player, and study two roles for graphical user interface (GUI) agents in this process: (1) as an objective evaluator, for which we introduce PlaytestArena, a new evaluation environment that pairs 200 browser-based game generation tasks across eight genres with rubrics of expected in-play behaviors, adjudicated by a GUI agent that loads each build in a browser and plays it; and (2) as a subjective playtester, for which we propose Play2Code, where a game agent and a GUI agent operate in a sustained loop with shared memory, turning game generation into a dialogue between coding and playing. Our experiments show that even frontier models struggle to generate playable games directly, while Play2Code achieves a 66.8\% rubric pass-rate, improving over single-pass and agentic-coding baselines by 37.1 and 14.6 points respectively. Further analysis shows that GUI playtester feedback is more traceable than a human report, yet idiosyncratic in ways reminiscent of human testers, establishing game playtesting as a critical testbed for interactive code generation. Our project website is available at https://continual-game-generation.vercel.app/. |
| title | GUI Agents for Continual Game Generation |
| topic | Software Engineering Artificial Intelligence Computer Vision and Pattern Recognition Human-Computer Interaction |
| url | https://arxiv.org/abs/2605.28258 |