牛津论文发现前沿 LLM 智能体难以与陌生伙伴零样本协同
牛津 BOLD 团队论文研究 LLM 智能体的零样本协同，在 9 个小型合作博弈中测试基于 GPT-5.2、Gemini 3 Pro 等模型的文本和代码智能体，发现它们难以与陌生伙伴协同，因为各自把自己临时约定的规则当作显而易见的选择。
Rohan Paul· @rohanpaul_ai · X·2026-11-08 02:45· 1 小时前AI 评分60
AI 导读
牛津 BOLD 团队论文研究 LLM 智能体的零样本协同（ZSC），在 9 个小型合作博弈中测试基于 GPT-5.2、Gemini 3 Pro 等模型的文本和代码智能体。
正文 · 原文
New Oxford paper finds that frontier LLM agents fail to coordinate with unfamiliar partners because each one treats its own made-up rules (arbitrary convention) as the obvious choice.
Agents from different companies increasingly must work together with no agreed rules. Past studies used shared scaffolding or complex games that hide why coordination fails.
They tested text and code agents built on models like GPT-5.2 and Gemini 3 Pro in 9 small cooperative games. In Cat & Dog, a safe move guarantees 5 points, while a signal convention pays 10 only if both agents pick the same one.
Paired with other models, text agents scored well below that safe 5, each calling its own arbitrary convention natural. A short shared statement of coordination principles, called a Coordination-friendly definition, led agents to reliably take the safe 5.
If your agent must work with agents you did not build, tell it to avoid unstated conventions and prefer actions any partner reads correctly.
来源：Rohan Paul · x.com
来源：RadarAI · aihot.news