HuggingFace Daily Papers（社区热门论文）· HuggingFace Daily Papers（社区热门论文）·· 6 天前AI 评分40
RSIGame：基于递归自我改进的自主智能体游戏开发框架
AI 导读
RSIGame 是一个带递归自我改进的自主智能体游戏开发框架，通过局部“探索-诊断-改进”循环与全局质量跟踪循环，缓解迭代优化对少量测试用例的过拟合。在 140 个 GameCraft-Bench 任务、两个游戏引擎和五个生成器上，RSIGame 在相同开发预算下持续提升游戏质量。
正文
Authors:Wenyi Wu, Minghao Fu, Jieyu You, Kun Zhou, Siqi Liu, Aayush Salvi, Yiheng Lin, Ce Zhang, Xiaohan Lan, Jiahui Zhu, Yujie Zhong, Qi She, Biwei Huang
Abstract:Recent advances in large language models have made automatic game generation increasingly feasible, yet reliably improving generated games beyond a playable version remains challenging. Naive iterative refinement can easily overfit a small set of test cases, producing fragile games with unresolved bugs, missing behaviors, and poor generalization to broader player interactions. We introduce RSIGame, an autonomous agentic game development framework with recursive self-improvement. RSIGame organizes development into complementary local and global loops. Concretely, a local explore-diagnose-improve loop broadly explores the executable game, diagnoses and prioritizes discovered issues, and performs evidence-grounded revision, where an evolving checklist continually accumulates new testing and improvement guidance. A global loop tracks overall quality, preserves the best checkpoint, and detects saturation or regression over long-horizon development. Beyond test-time improvement, RSIGame further internalizes successful development experience into the generator through training. Across 140 GameCraft-Bench tasks, two game engines, and five generators, RSIGame consistently improves game quality under matched development budgets. Notably, experience internalization enables Qwen3.8-27B to reach 61.38 on Godot and 58.53 on Phaser, exceeding GPT-5.5 one-shot scores while reducing Qwen's generation tokens by 11 times.
| Subjects: | Computation and Language (cs.CL); Computer Science and Game Theory (cs.GT); Machine Learning (cs.LG); Multiagent Systems (cs.MA) |
| Cite as: | arXiv:2609.39045 [cs.CL] |
| (or arXiv:2609.39045v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2609.39045 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Wenyi Wu [view email]
[v1]
Wed, 30 Sep 2026 05:54:34 UTC (15,214 KB)
来源：HuggingFace Daily Papers（社区热门论文） · arxiv.org