A Self-Calibrating Framework for Analog Circuit Sizing Using LLM-Derived Analytical Equations

arXiv:2604.07387 · cs.AR, cs.AI · Submitted 2026-04-08 · Read on arXiv

cs.AR, cs.AI

Submitted: 2026-04-08

Updated: 2026-10-05

Comments: 14 pages, 4 figures, 7 tables, plus supplementary. V3: Extended to 8 topology families (6-30 transistors) across 6 process nodes with 5-trial statistics; adds cross-model evaluation (5 LLMs), ablation study, matched TuRBO-1 baseline, and structural audit of 2,634 LLM-derived equations

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Calibration — 2× in this paper · explained in 7 episodes
• Accuracy — 1× in this paper · explained in 1 episode
• Benchmark — 1× in this paper · explained in 2 episodes
• Large Language Model (LLM) — 1× in this paper · explained in 3 episodes

Sources

• AutoSizer: Automatic Sizing of Analog and Mixed-Signal Circuits via Large Language Model (LLM) Agents
• TopoSizing: An LLM-aided Framework of Topology-based Understanding and Sizing for AMS Circuits
• EasySize: Elastic Analog Circuit Sizing via LLM-Guided Heuristic Search
• AmpAgent: An LLM-based Multi-Agent System for Multi-stage Amplifier Schematic Design from Literature for Process and Performance Porting

Related papers

• WitCert: Sound Runtime Risk Observability and Gating for KV-Cache Quantization
• Golden Ruler: A Numeric Format Catalog with Bit-Exact Conformance Vectors for FP8, BF16, MXFP4, and Microscaling Formats
• RFChipAgent: Multi-Agentic AI Flow for Analog/RF Chip Design
• PoisonCap: Efficient Hierarchical Temporal Safety for CHERI
• Provisioning to Runtime Optimization of a 100 MW-Scale AI Cluster
• Bit-Accurate Modeling of GPU Matrix Multiply-Accumulate Units: Demystifying Numerical Discrepancy and Accuracy