快讯
Google 与 MIT 报告推出 Coco：面向软硬件协同设计的智能体平台
dair_ai 援引 Google 与 MIT 的报告介绍 Coco——一个供 TPU 架构师用于硬件与模型协同设计的智能体平台。报告称，每次设计决策依赖数百 GB 训练前未见过的全新仿真扫描数据；Coco 将每次扫描登记到规范化的关系数据库中，智能体报告的每个数字均可通过 SQL 查询溯源。智能体可自主组合类型化工具、运行对比相同执行配置下系统等重复性分析，并读取 UI 导航状态作为上下文。报告称短期目标是将架构师搭建仿真和获取洞察的时间减半。论文链接：arxiv.org/abs/2610.02376。
事件来源
查看原文
Great report from Google and MIT. Co-designing ML models and the accelerators is an exciting research direction. This report introduces Coco, an agent platform TPU architects use for hardware and model co-design. Each decision depends on hundreds of gigabytes of fresh simulation sweeps that no model saw during pretraining. Coco registers every sweep in a normalized relational database, so each number an agent reports comes from a SQL query. Agents compose typed tools on their own, run recurring analyses such as comparing systems at matched execution configurations, and read the UI's navigation state as context. The near-term goal is halving the time architects spend setting up simulations and getting insights from them. Paper: https://arxiv.org/abs/2610.02376 Chat with Paper: https://academy.dair.ai/papers/coco-an-agentic-copilot-for-the-hardware-software-co-design-lifecycle-2610.02376