AI 热点

DeepMind 与哥大用 SQLite 让 AI 智能体调试芯片仿真

Rohan Paul更新于 11月16日 08:46

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.

AI 导读

Google DeepMind 与哥伦比亚大学的论文提出 Back-to-the-Future(BTTF),把超过 10 GB 的芯片仿真波形转成紧凑的 SQLite 数据库,让智能体用 SQL 查询调试。在 150 个专家标注的验证问题上,使用 Gemini 2.5 Pro 的 BTTF 正确率达 95.33%;多智能体分工在质量审计上比单智能体高 17.3%,延迟为 1.96 倍。

正文

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.

来源

Rohan Paul