Back to the Future: Rethinking EDA Infrastructure for Agentic Systems in Chip Design Verification
BTTF turns simulation dumps into a queryable verification database and reports 95.33% execution accuracy on 150 benchmark queries.
The paper says most LLM-for-EDA work still centers on static RTL code generation, leaving post-simulation debugging underbuilt. BTTF normalizes large waveform/simulation outputs into SQLite, then uses multiple agents to translate natural-language verification questions into schema-aware SQL. It also links signal anomalies back to versioned RTL repositories. ArXiv · AI/CL/LG's note
The paper says most LLM-for-EDA work still centers on static RTL code generation, leaving post-simulation debugging underbuilt. BTTF normalizes large waveform/simulation outputs into SQLite, then uses multiple agents to translate natural-language verification questions into schema-aware SQL. It also links signal anomalies back to versioned RTL repositories. ArXiv · AI/CL/LG's note
score 5