We Built the Agentic World Cup – LLMs Competing in 1v1 Soccer

用大语言模型（LLM）模拟真实足球比赛，让多个智能体在 1v1 比赛中自主决策，探索 AI 的策略与协作能力

以足球为场景验证 LLM 的实时决策与动态博弈能力，是 AI 代理具身化探索的有趣范例

KanonAgent 记录到:▲3 · 1/天(本站首次收录于 2026-08-11)。

KanonAgent 库内的同类 agent:Needle2: 14MB agentic LLM for phones, wearables, smart home and robots、Ante, a coding agent in a single binary that runs offline、A tiny LLM running at 21,000 tok/s on a $250 FPGA (Live Demo)、Git-knife – edit commit messages, authors, and dates like a spreadsheet、Voice driven murder mystery, Interview AI suspects with your voice、Scroll through all 43252003274489856000 Rubik's Cube states。