aifollow.news
返回 Rohan Paul
Rohan Paul· @rohanpaul_ai · X· · 原发布时间 AI 评分54

Google DeepMind 与 Columbia Univ 研究用可查询数据库辅助 AI 排查芯片仿真问题

AI 导读

这项论文介绍的 Back-to-the-Future(BTTF)把庞大的芯片仿真波形记录转换为 SQLite 数据库,再由多个 AI 代理将自然语言问题转成 SQL 查询、检查设计规则并审核答案。所引介绍称,系统使用 Gemini 2.5 Pro 回答 150 道专家标注的验证问题,正确率为 95.33%;多代理方案的质量审核得分较单代理高 17.3%,但延迟为 1.96 倍。

原帖引用 · 原文

该语言的正文暂不可用,当前显示已有版本。

@rohanpaul_ai

– https://t.co/L1B9dmaErD

Title: "Back to the Future: Rethinking EDA Infrastructure for Agentic Systems in Chip Design Verification"

回复Rohan Paul@rohanpaul_ai
Google DeepMind and Columbia Univ paper argues that AI agents can debug chip simulations once the huge waveform files become a SQL database they can query. Chip simulations record every signal change, and these dumps can exceed 10 GB of text that engineers still scan by hand. No LLM context can hold that, and the files offer no way for an agent to search them. They built Back-to-the-Future (BTTF), which converts the dumps into a compact SQLite database. A team of agents then turns plain-English questions into SQL, checks design rules, and audits each answer. On 150 expert-labeled verification questions, it answered 95.33% correctly using Gemini 2.5 Pro. Splitting the work across specialized agents scored 17.3% higher on a quality audit than 1 agent alone, at 1.96x the latency. If your agents struggle with huge logs or traces, put the data in a queryable database instead of pushing it into the prompt.
在 X 查看这条帖子 ↗

来源:Rohan Paul · x.com

论文
发现内容有误?提交纠错