Metraipolis › archive › dc_e088d3d43fa7
GAMEGO: Training Game-Dev Agents with Synthetic Trajectories Anchored in Real-World Assets — arXiv:2610.06910
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.06910
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T11:18:07.686Z
- SHA-256 of the archived text
e012da833ab21985183d3e5fdb1d753560671dd22dfece78e596d33bc784db5a- Stable URL of this page
https://metraipolis.com/documento/dc_e088d3d43fa7
How to cite
GAMEGO: Training Game-Dev Agents with Synthetic Trajectories Anchored in Real-World Assets — arXiv:2610.06910 — arXiv (en), https://arxiv.org/abs/2610.06910 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e088d3d43fa7 (Metraipolis archive dc_e088d3d43fa7, sha256 e012da833ab21985183d3e5fdb1d753560671dd22dfece78e596d33bc784db5a)
BibTeX
@misc{dce088d3d43fa7,
title = {GAMEGO: Training Game-Dev Agents with Synthetic Trajectories Anchored in Real-World Assets — arXiv:2610.06910},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.06910},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e088d3d43fa7; sha256 e012da833ab21985183d3e5fdb1d753560671dd22dfece78e596d33bc784db5a},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.06910. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Recent advances in Large Language Models (LLMs) have demonstrated remarkable capabilities in web front-end execution, with browser-based game generation emerging as a particularly prominent frontier. While previous efforts frequently rely on complex multi-turn workflows or focus on static game evaluation benchmarks, this work targets direct end-to-end real-world game synthesis driven by coding agents. However, generating complex games directly from sparse user queries often forces coding agents to make underspecified assumptions, yielding incomplete mechanics, disconnected gameplay flows, and limited visual aesthetics. To resolve this issue, this paper presents GameGo, a scalable framework that systematically transforms brief game seeds into comprehensive Product Requirements Documents grounded in industry game-development practices. To retain core gameplay constraints without restricting design exploration, GameGo uses task-specific dynamic compression to maximize information density while preserving instruction following. Based on this pipeline, GameGoData is constructed with 55,060 development trajectories across 2D, 2.5D, and 3D games, alongside GameGoBench, a benchmark comprising 124 diverse game queries. Training GameGoCoder on GameGoData yields a model that outperforms matched baselines and is comparable to frontier models across gamedev benchmarks. All code, datasets, and models will be made publicly available. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2610.06910 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-07T11:15:24.452Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).