发表机构
Institute of Automation, Chinese Academy of Sciences; Beijing Zhongguancun Academy（中国科学院自动化研究所; 北京中关村学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
JEV-Star结合快速JEV动作选择与GPT-6规划，以低成本击败星际争霸II内置AI Lv7，显著提升胜率与敌方消灭率，展示了亚秒级决策与长期规划的有效分工。
AI 中文摘要
我们提出了JEV-Star，一种星际争霸II控制器，通过将快速的JEV动作选择与持续的GPT-6规划相结合，击败了最强的非作弊内置AI（Lv7）。该系统在Lv5至Lv7难度下赢得了四场完整比赛，包括两场不同随机种子的Lv7胜利，同时保持了0.422秒的中位JEV响应时间。这些比赛的平均估计模型成本约为每场3.71美元：JEV约0.15美元，GPT-6约3.56美元。我们将该系统与仅使用JEV的初始控制器在整场宏观控制和多单位微操方面进行了比较。独立控制器在Lv2难度下达到20分钟限制而未扩张。在35张战斗地图上，每个控制器每张地图进行三个回合，组合系统将平均敌方消灭率从16.50%提升至37.69%，胜场数从105场中的3场增加到7场。回放帧和决策日志记录了成功完整比赛中的资源预留、持续经济目标和稳定的军队目标。结果表明，廉价、亚秒级决策与更长视野规划之间存在实际分工。该比较评估了完整系统；并发的接口改进意味着规划的贡献并未通过受控消融实验单独隔离。代码可在https://github.com/sc2musa/Jev_Star获取。
英文摘要
We present JEV-Star, a StarCraft II controller that defeats the strongest non-cheating built-in AI, Lv7, by combining fast JEV action selection with persistent GPT-6 planning. The combined system wins four full games at Lv5--Lv7, including two Lv7 victories with different seeds, while retaining a median JEV response time of 0.422 seconds. Mean estimated model cost across these games is USD~3.71 per game: USD~0.15 for JEV and USD~3.56 for GPT-6. We compare this system with an initial JEV-only controller in full-game macro control and multi-unit micromanagement. The standalone controller reaches a 20-minute limit against Lv2 without expanding. Across 35 battle maps with three episodes per map and controller, the combined system raises mean enemy elimination from 16.50\% to 37.69\% and wins from 3 to 7 out of 105. Replay frames and decision logs document resource reservation, persistent economic goals, and stable army objectives in successful full games. The results demonstrate a practical division between inexpensive, subsecond decisions and longer-horizon planning. The comparison evaluates complete systems; concurrent interface improvements mean that planning's contribution is not isolated by a controlled ablation. Code is available at https://github.com/sc2musa/Jev_Star
