EvoDRC framework automates DRC violation repair using evolving LLM agents

Researchers have developed EvoDRC, a novel framework designed to automate the repair of design rule check (DRC) violations in advanced-node physical design. This system utilizes a skill-evolution approach where layer-specific repair skills are initially distilled from a reference design and then continuously refined using experience gained from the target design. EvoDRC employs LLM agents assigned to specific layout regions, supported by local DRC analysis, connectivity checking, and impact preview tools to ensure modifications are effective and do not introduce new issues. Experiments on the DAC26 DRC Benchmark demonstrated a significant overall reduction in violations compared to existing methods. AI

IMPACT This framework could significantly speed up chip design by automating a complex and time-consuming manual process.

RANK_REASON The cluster contains an academic paper detailing a new framework and its experimental results. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.AI →

• arXiv
• DAC26 DRC Benchmark
• EvoDRC

• paper
• product

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →