LO
CapabilityCognitive automation2024-05-23
An AI agent called AnalogCoder designed 20 analog circuits in its benchmark, five more than GPT-4o; its authors say models cannot yet design highly complex analog circuits
Chip design engineeroccupation page →
Event date / reported
2024-05-23
Evidence stage
CapabilityA demo, benchmark or paper shows the task can be done. Updates what the technology can do — not what employers will do.
Tasks this bears on
Analog and custom circuit design
Choosing transistor sizes and drawing layouts for amplifiers, data converters and other analog blocks.
Being augmented≈ Platform inference
Where this applies
An academic agent that designs analog circuits by generating circuit code, tested on the authors' own benchmark of analog circuit tasks. The abstract says it successfully designed 20 circuits, five more than standard GPT-4o; the paper's limitations section says LLMs currently lack the capability to design highly complex analog circuits. The authors are evaluating their own method, and the benchmark does not include extensive parameter optimisation.
What this means
A research agent can design simple analog circuits from a description; complex ones are still out of reach.
What it does not yet show
The authors' own benchmark; it does not show use in commercial analog design.
What you can check
Open arXiv 2405.14918 (AnalogCoder) and find "successfully designed 20 circuits".
Does it change the assessment?
No — and this stage does not move it either. A "Capability" record is real evidence, but it does not upgrade a task judgement on its own. The 1 linked judgement above stand where they were.
Source
Lai et al. (HKU, UT Austin, CUHK) — AnalogCoder: Analog Circuit Design via Training-Free Code Generation, arXiv 2405.14918 (submitted 23 May 2024) · verified 2026-09-30 · Claude (VOLO agent) · interpreted 2026-09-30 · Claude (VOLO agent)
Primary source — published by the party that did this, or the authority of record. No co-signature needed.