Virtual process engineer improves lithography recipe accuracy significantly
VPEvolve: A Self-Evolving Virtual Process Engineer for Computational Lithography
Artificial IntelligenceSoftware Engineering
Summary
Improving tiny features on computer chips is tricky because small corrections can affect other parts unpredictably. The authors present a virtual assistant grounded in measured experience and language models that suggests safe recipe changes to fix these problems. It learns from each trial to make better adjustments without changing its core brain. This approach achieved much more accurate chip patterns in tests and met strict quality targets every time.
What this means in practice
- •For semiconductor process engineers: Enhance lithography correction recipes with automated suggestions that systematically reduce edge placement errors and meet quality constraints.
- •For fab automation teams: Integrate virtual process engineers to analyze, update, and validate OPC recipes using commercial tools and measured feedback.
Authors
Tianyi Li, Wenxuan Dong, Donger Luo, Nan Wang, Yanpeng Chen, Jiaqi Liu, Xinyun Zhang, Hao Geng
Abstract
Optical proximity correction (OPC) recipes grow as engineers add local rules to repair newly discovered lithography hotspots. Each correction can interact with existing rules, while lessons from commercial-tool trials remain scattered across code and logs. \system combines a Virtual Process Engineer (VPE) harness with a Skill Bank of measured engineering experience. The harness equips a frozen language model with process manuals, layout analysis, recipe editing, and commercial-tool evaluation. The actor proposes changes to the global parameters, local targeted rules, or diagnostic trials. After each evaluation, an LLM reflector and curator turn the measured response into evidence-linked judgments. The actor retrieves them before its next trial. Feasible improvements update the retained recipe; every measured trial informs the Skill Bank that guides the next edit. The model weights remain fixed. On a FreePDK45-derived benchmark with ten commercial-tool evaluations per case, \system reduces the mean per-case maximum edge placement error from 18.294 to 5.361 nm on Poly and from 22.052 to 15.692 nm on Metal1. Every final recipe satisfies the predefined quality constraints and improves the maximum error by at least 0.1 nm.