Understand this story
Researchers from Google DeepMind and Columbia University have proposed a method called Back-to-the-Future (BTTF), which converts chip simulation waveforms exceeding 10 GB into a compact SQLite database, enabling AI agents to perform debugging through 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 1.96 times that of a single agent. The work is currently publicly available as a paper, with no follow-up progress reported yet.
AI-generated from public reports
Latest development · Report
DeepMind and Columbia Use SQLite to Let AI Agents Debug Chip SimulationsDevelopments
1 confirmed developments
Reports and discussion timeline
Browse reports and discussion by time. Their evidence levels remain distinct.
Nov 16
Rohan Paul
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.
AI Trends