Meta AIRA₃ 自主科研系统 Kaggle 夺金
Rather than relying on a central controller, AIRA₃ runs many long-running agents (pairs of models + coding harnesses) in their own isolated environments and coo
Meta 的自主 AI 研究系统 AIRA₃ 在 NVIDIA 举办的 Kaggle 竞赛中从约 4000 支队伍中排名第 8，获金牌，任务为微调 30B Nemotron 模型以提升推理能力。该系统不依赖中央控制器，而是让多个长时运行的智能体在隔离环境中通过共享论坛与文件系统异步协作。其夺金组合为 GPT 5.5（配 OpenCode）+ Claude 4.8（配 Claude Code），内部基准中还在生产 GPU kernel 上实现 27% 延迟降低。
正文
当前显示原文，中文全文译文尚未就绪。
Rather than relying on a central controller, AIRA₃ runs many long-running agents (pairs of models + coding harnesses) in their own isolated environments and coordinates asynchronously through two shared substrates:
1️⃣ a forum for sharing hypotheses and findings 2️⃣ a shared filesystem for solution artifacts
The individual agents collaborate, share discoveries, and build on each other’s work. As the graph below demonstrates, the system uses compute to compound knowledge and drive performance gains over time. Search strategies emerge dynamically as each agent decides which discoveries to build upon.