DRC-Aid: Design-Rule Correction via Agentic Framework utilizing Inference-Time Large Language Models

2026-07-23

AI Summary

This work addresses the heavy reliance on manual intervention in repairing design rule violations (DRVs) in integrated circuit layouts by proposing the first agent framework that integrates a large language model (LLM) into a closed-loop physical verification system. The approach combines a deterministic rule engine to generate constrained geometric edit operations with an LLM that makes context-aware decisions based on local layout geometry. Efficient exploration of repair paths is achieved through depth-first search, backtracking, and global memory, ensuring electrical topology equivalence while automating corrections. Evaluated on FreePDK45, the method successfully produces DRC-clean and LVS-equivalent fixes in 92.5% of test cases, reducing total violations by 98%. The LLM-driven strategy substantially outperforms random (54.4%) and heuristic (83.3%) baselines, demonstrating particular strength in complex, multi-violation scenarios.

Abstract

Resolving Design Rule Violations (DRVs) in layouts entails an iterative loop of geometric edits and verification. We present DRC-Aid, a closed-loop agentic framework that automates local DRC repair by formulating it as verification-in-the-loop search. To constrain the combinatorial geometric repair space, a deterministic Rule Engine converts physical verification tool-reported violations into a bounded menu of geometric edits. An off-the-shelf Large Language Model (LLM) evaluates local geometric context to select edits from this menu, with budgeted depth-first search and backtracking. Immediate feedback from verification tools such as Calibre nmDRC/nmLVS enforces geometric compliance and guards against electrical-topology degradation, while a global Memory Bank prevents cyclic re-exploration. Evaluated on FreePDK45 layouts containing DRVs, DRC-Aid achieves DRC-clean, LVS-equivalent repairs in ~92.5% of cases with a ~98% total violation reduction, while residual cases yield partially repaired LVS-equivalent candidates. Under an identical search and verification infrastructure, LLM-based selection outperforms random (54.4%) and deterministic-heuristic (83.3%) policies, with the gap widening on cases with six or more violations.

Problem

• Design Rule Violations
• DRC Repair
• Layout Verification
• LVS Equivalence
• Geometric Compliance

Innovation

• Design Rule Correction
• Agentic Framework
• Large Language Model
• Verification-in-the-loop
• Geometric Repair