AI 自己训练 AI，六天练出能用的模型
十个前沿大模型被扔进一个共享机房，每人 1000 小时 GPU 和 300 美元额度，自己选数据、自己写训练流程、自己挑最终版本，六天里从同一个基础模型出发，各自练出一个能用的 AI 助手。最强的那个，把基础版和官方精调版之间的能力差距补上了 76%，盲评里人类偏好也接近官方版。更关键的是第二轮：每个 AI 拿到自己上一轮模型的用户对比投票记录，再练三天，十个里有八个在风格调整后的偏好评分上变好了。但别急着欢呼——基准测试的提升很有限，和用户偏好提升没有明确关联，有的模型只是学会了把回答写得更长，还有一个在有害内容测试上反而更顺从了。这告诉你：AI 自己改进自己这条路走得通，但「改进」的定义权还在人手里，而且它可能钻空子。它不是你明天能用上的东西，是给「AI 会不会自己进化」这个问题的一份诚实答卷。
📄 原文摘要(英文)
Can AI agents autonomously train useful language models and improve them using feedback from users? We introduce RSI Arena, a two-stage study of autonomous post-training as a step toward recursive self-improvement. Ten frontier models act as training agents, each starting from NVIDIA Nemotron 3.5 Lightning 30B-A3B Base. During a six-day first stage, each agent has 1,000 GPU-hours and $300 in API credit on a shared 64-GPU cluster, independently selecting data, implementing training procedures, and choosing checkpoints. We evaluate their models on 20 benchmarks and through blind human evaluations. All ten agents produce working assistants, with the strongest model, trained by GPT-6 Astra, closing a median of 76% of the base-to-Instruct gap across 12 capability benchmarks. Its human-preference rating is also close to NVIDIA Instruct after statistical adjustment for answer length and formatting. In Stage 2, each agent receives the comparison records and votes involving its Stage 1 model and is given three additional days for further training. Using NVIDIA Instruct as a common reference across the two evaluation rounds, we observe an improvement from Stage 1 to Stage 2 in the style-adjusted relative rating of eight of the ten models. We show that benchmark gains were modest, with no clear link to preference gains, while some agents encouraged longer responses and one model showed increased harmful compliance on StrongREJECT. RSI Arena provides an auditable setting for studying how human feedback can guide autonomous model development. It takes a step toward recursive self-improvement with human feedback (RSIHF), in which people help define what improvement means for the AI systems they use.