AI Paper Atlas

Research map / Large language models / Agents, code and math

AutoSizer: Automatic Sizing of Analog and Mixed-Signal Circuits via Large Language Model (LLM) Agents

Xi Yu, Dmitrii Torbunov, Soumyajit Mandal, Yihui Ren

ICML 2026 · Large language models › Agents, code and math · approach: Agent instruction-following benchmarks · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add circuit understanding (CU) module (ablation)AutoSizer · AMS-SizingBench ablation (5 circuits)FOM: 28.65 -> 35.47Improved
add self-reflection loop (SRL) (ablation)AutoSizer · AMS-SizingBench ablation (5 circuits)FOM: 25.32 -> 35.47Improved
add LLM-guided adaptive optimization engine instead of fixed BO (ablation)AutoSizer · AMS-SizingBench ablation (5 circuits)FOM: 27.00 -> 35.47Improved
add initial search space decision without circuit understanding (ablation)AutoSizer (w/o CU) · AMS-SizingBench ablation (5 circuits)FOM: 33.43 -> 28.65Hurt
use AutoSizer instead of LEDRO on Hard circuitsLLM sizing agents · AMS-SizingBench Hardsuccess rate: 80.0% -> 100%Improved
use LLM-based agents instead of traditional optimizerscircuit sizing · AMS-SizingBench Hardsuccess rate: 50.0% (GA) -> 80.0% (LEDRO)Improved
use LLM-based agents instead of traditional optimizerscircuit sizing · AMS-SizingBench Easy and MediumFOMNo clear effect
add self-reflection to LLM search directions (ADO-LLM lacks it)ADO-LLM · AMS-SizingBench Hardsuccess rate: 41.0% (ADO-LLM) -> 100% (AutoSizer)Improved
use LLM-only sizing without explicit optimizer (EE-Sizer)EE-Sizer · AMS-SizingBench Easyruntime (s): 257.0 -> 756.2Hurt
allow expand/unfix action in outer loop on hard circuitsAutoSizer outer loop · AMS-SizingBench HardFOM change: +16.4%Improved
narrow ranges actionAutoSizer outer loop · AMS-SizingBench HardFOM change: -3.8%Hurt
use Fixed trust-region TuRBOTuRBO · AMS-SizingBench Easysuccess rate: 39.8% vs 93.3% (Genetic)Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy