aifollow.news
Back Rohan Paul
Rohan Paul· @rohanpaul_ai · X· · Original publication time AI score54

Google DeepMind and Columbia Univ study uses a queryable database to help AI agents debug chip simulationsMachine translation

AI introduction

The researchers built Back-to-the-Future (BTTF) to convert large chip simulation dumps into a SQLite database. A team of agents translates plain-English questions into SQL and audits the answers. Using Gemini 2.5 Pro, the system answered 95.33% of 150 expert-labeled verification questions correctly. The specialized-agent approach scored higher than a single agent on a quality audit, with 1.96 times the latency.

Original post · Original

The article text is unavailable in this language; an existing version is shown.

@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.

Source: Rohan Paul · x.com

Research
Found an error? Send a correction