Mobile QR Code
Title RAG Prompting and DQN Reinforcement Learning-based Integrated Framework for 2stage-OpAmp Layout Automation and LPE Performance Optimization
Authors 우성영(Seong Young Woo) ; 연혜은(Hye Eun Yeon) ; 김영식(Young Sik Kim)
DOI https://doi.org/10.5573/ieie.2026.63.2.19
Page pp.19-31
ISSN 2287-5026
Keywords RAG prompting; DQN reinforcement; DRC/LVS mismatch; Integrated framework; Optimization
Abstract This study proposes a framework for the automated layout generation of an analog circuit by employing RAG prompting to automate placement and routing where DQN reinforcement learning is used to correct DRC/LVS mismatches iteratively. Furthermore, Layout Parasitic Extraction(LPE) is incorporated to compare the results between schematic and layout Netlist, and the reinforcement learning is applied to minimize performance discrepancies. Through this approach, we implement an automated integrated framework that encompasses layout generation, verification, and optimization.