DeepMind and Columbia Use SQLite to Let AI Agents Debug Chip Simulations
A paper from Google DeepMind and Columbia University proposes Back-to-the-Future (BTTF), which converts over 10 GB of chip simulation waveforms into a compact SQLite database, allowing agents to debug using SQL queries. On 150 expert-annotated validation questions, BTTF using Gemini 2.5 Pro achieved an accuracy of 95.33%; multi-agent division of labor was 17.3% higher than a single agent on quality auditing, with a latency of 1.96 times.
Body
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.
AI Trends