AutoTavern 让 LLM 智能体自治研究，做出比肩炉石顶级玩家的 AI
Build, Don't Play: Self-Improving LLM Research Agents Develop a Hearthstone Battlegrounds AI That Rivals Top Players
一群 LLM 智能体自己搞研究，20 天造出炉石酒馆战棋 AI，天梯 80% 吃鸡率超过服务器前十玩家，还能 0.03 秒决策，论文要开源。
arXiv 论文介绍 AutoTavern，一套由专用 LLM 研究智能体组成的自改进系统，用于炉石传说酒馆战棋。20 天内智能体搭建出完整还原线上游戏的 TavernGym 模拟器，并用 PPO 训练出 23 个版本的 TavernAgent。TavernAgent 天梯评分从 6,000 升至约 15,000，最近 20 场平均名次 1.60、吃鸡率 80%，各项数据均优于服务器前十玩家（2.34、59%）。在 960 题的 TavernBench 上，TavernAgent 答对 91% 的对局任务，前沿 LLM 最高 63%，且决策仅需 0.03 秒，对方最多需 26 秒。结论是 LLM 智能体做研究的产出远强于它们自己玩游戏。
Build, Don't Play: Self-Improving LLM Research Agents Develop a Hearthstone Battlegrounds AI That Rivals Top Players
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.