AI 自己造了个游戏 AI，把人类高手打穿了
让 AI 直接玩炉石，它打不过顶尖玩家；但让 AI 去造一个能玩炉石的 AI，它赢了。研究者搭了个自改进系统：几个大模型研究员共享记忆、互相验证、用真实对局反馈迭代，20 天从零复刻了整款游戏，再训练出 23 个版本的智能体。最后这个智能体自己上排位，从 6000 分打到 15000，最近 20 局平均名次 1.60、80% 第一，服务器前十名玩家的平均名次是 2.34、59% 胜率——每一项都输给它。更狠的是，它每步决策只要 0.03 秒，而直接让大模型玩，正确率只有 63%，还要想 26 秒。结论很直白：大模型自己下场不行，但让大模型当研究员去造工具，它能把人类比下去。这不是你明天能用上的东西，但它重新划了一条线——AI 的价值可能不在前台表演，而在后台造引擎。
📄 原文摘要(英文)
Can LLM agents carry a hard real-world problem from raw data to a system that holds its own against people? We study this in Hearthstone Battlegrounds, an eight-player auto-battler with stochastic shops and battles, hidden information and nearly a thousand interacting cards. We present AutoTavern, a self-improving research system: specialised LLM research agents share a typed research memory, every claim passes verification gates, and live games close the loop, so the agents improve the simulator, opponents and policy and, from the same feedback, their own research process; a human sets goals and rules on ambiguous mechanics. In 20 days AutoTavern built TavernGym, the first faithful, full-content reproduction of the live game, and delivered 23 versions of TavernAgent, trained with PPO against opponents calibrated to real games. TavernAgent plays complete games on the live ladder by itself: its rating rose from 6,000 to about 15,000 and, on the public leaderboard's measure, its last 20 records average a placement of 1.60 with 80% first places, better than the server's ten highest-rated players on every statistic (2.34, 59%). TavernBench, 960 tasks in 40 scenarios, shows that the system the agents built is the strongest player: TavernAgent answers 91% of the play tasks against at most 63% for frontier LLMs, and decides in 0.03 s where they need up to 26 s; within the second a live turn allows, it keeps 90% and no LLM more than 26%. LLM agents build far better than they play. We will open-source TavernBench and TavernGym at https://github.com/MCG-NJU/AutoTavern.