Meta 的 AIRA₃ 在 NVIDIA Kaggle 竞赛中获第 8 名金牌
We entered AIRA₃ with an ensemble of models in the live competition, and also assessed it with several others post-hoc. The 8th ranked gold medal entry ensemble
Meta 在 6 月让自主 AI 研究系统 AIRA₃ 参加 NVIDIA 在 Kaggle 举办的竞赛，任务是对一个 30B Nemotron 模型做微调以提升其推理能力，AIRA₃ 在约 4000 支队伍中排名第 8，获得金牌。AIRA₃ 不依赖中央控制器，而是让多组模型加编码工具在隔离环境中长时间运行，通过共享论坛和共享文件系统异步协作。赛后 Meta 还用 Muse Spark 1.2（配 MuseCode）等模型做了评估，其中 Muse Spark 1.2 达到金牌水平，Muse Spark 1.1 和 GLM 5.2 达到银牌水平，这些赛后提交在与现场竞赛相同的私有测试集上由外部评分。
推荐理由
AI 评分 55
Meta 公开 AIRA₃ 在 Kaggle 竞赛中的名次与模型组合，可看到自主研究系统在真实赛题上的表现。
主题
正文
当前显示原文，中文全文译文尚未就绪。
We entered AIRA₃ with an ensemble of models in the live competition, and also assessed it with several others post-hoc. The 8th ranked gold medal entry ensemble was a combination of GPT 5.5 (w/ OpenCode) + Claude 4.8 (w/ ClaudeCode).
Post-hoc we assessed with Muse Spark 1.2 (w/ MuseCode), which also performed at a Gold Medal level, as well as Muse Spark 1.1 (w/ OpenCode) and GLM 5.2 (w/ OpenCode), both of which achieved Silver Medal level performance. The post-hoc submissions were also graded externally on the same private test set as those made during the live competition.