AI 管足球俱乐部 20 年，大模型全活下来了
大模型做单次任务已经够可靠，但能不能在长周期里持续做对决策，一直没人测过。FM-Bench 让 15 个前沿模型各当一支足球队的经理，管 20 个赛季，要转会、谈合同、建青训、排阵容，还得应付可能炒你的董事会。结果出人意料：所有模型都撑完了 20 年，而盲目的脚本基线大多中途就死了。更反直觉的是，模型排名和算力、价格、厂商都没关系，决定胜负的是管理行为——高分模型会在赛季末减少慢回报投资、让现金流动起来、提前续约，而 token 花多少完全预测不了成绩。不过没有模型能从几百次被拒的报价里学会市场的隐藏价格，自我管理的记忆也都会失效。这不是你明天能用上的东西，但它第一次把『长周期决策』从口号变成了可测量的指标，也暗示了 AI 在复杂环境里的天花板可能不在算力，而在行为策略。
📄 原文摘要(英文)
Language model agents now execute bounded tasks reliably. Whether they can sustain effective decision-making over long horizons, where actions have cumulative consequences and the environment responds to their choices, remains largely unmeasured. FM-Bench (Football Management Benchmark) measures this. An LLM agent runs a football club for 20 in-game years through 26 tools and roughly 340 to 400 decision stops. It drafts a squad on the same budget as every rival, trades players, negotiates contracts, invests in facilities and youth, sets lineups, and answers to a board that can fire it, while a deterministic engine accumulates every year into one final score with no LLM judge or human rater. The solo track plays each of 15 frontier models against a frozen scripted world, and the Arena places the same models plus a scripted anchor in one shared 20-year world; to our knowledge, the first head-to-head evaluation at this scale. We measure six behavioral capabilities behind the score. Across three seeds, all 15 models complete every horizon while the blind scripted baselines die out in most of theirs, and claude-fable-5 tops the solo board on mean score and the Arena, where the title nonetheless rotates among ten models. Neither scale, price, nor vendor predicts the order; the order settles only late in the horizon, and the best first-play human lands only at the bottom of the model board. What separates the models is managerial behavior rather than computation. Higher-scoring models reduce slow-payoff investment near the end, keep cash invested rather than idle, and open renewals well before the deadline, while token spend predicts nothing. No model learns the market's hidden prices from hundreds of rejected bids, and self-managed memory fails in two opposite modes: an archive that only grows or a plan rewritten every season. Code is available at https://github.com/Analogy-AI/fm-bench.