Back to AI News
arxiv

AMSchem turns AMS netlists into readable schematics with a verifier-guided LLM agent

Researchers present AMSchem, a training-free agentic framework that automatically converts analog and mixed-signal netlists into human-readable schematics. The system splits circuit-aware visual planning (DrawingIntent) from executable schematic geometry (SchematicIR) and applies localized visual feedback with bounded, revalidated repair patches, while deterministic validators enforce device preservation, pin-net consistency and geometric correctness. On the 40-circuit schematic subset of the new AMSchem-Bench (64 circuits, 12 types), AMSchem with gpt-5.5 reaches 85.0% validity versus 32.5% for direct generation. Used as a visual feedback module in LLM-based analog design, it resolves all 13 previously failed cases from the AnalogCoder benchmark across five models.

AI Brief

It shows a concrete verifier-driven agent design that closes the netlist-to-schematic gap and measurably improves LLM-driven analog circuit design.

arXiv:2611.12333v1 Announce Type: new Abstract: For decades, the netlist-to-schematic gap has remained a persistent challenge in design automation, especially for analog and mixed-signal (AMS) circuits. Netlists encode connectivity, not visual presentation, making their manual conversion into readable schematics time-consuming and dependent on expert conventions. The same gap leaves LLM-based design tools without structured visual feedback, forcing them to iterate on circuits they cannot see. We present AMSchem, a training-free, verifier-guided agentic framework that automatically generates human-readable schematics from AMS netlists. AMSchem separates circuit-aware visual planning (DrawingIntent) from executable schematic geometry (SchematicIR), and applies localized visual feedback with bounded, revalidated repair patches. Deterministic validators enforce device preservation, pin-net consistency, and geometric correctness throughout. For evaluation, we construct AMSchem-Bench comprising 64 circuits of 12 types. On the 40-circuit schematic subset, AMSchem with gpt-5.5 achieves 85.0\% validity (vs. 32.5\% direct generation). When integrated as a visual feedback module in LLM-based analog design, AMSchem resolves all 13 previously failed cases from AnalogCoder benchmark across five models, substantially improving the success rate. Our dataset and benchmark are available at https://www.amschem.com/benchmark
Be the first to rate this article.

Comments & Questions (0)

Captcha
Please be respectful — let's keep the conversation friendly.

No comments yet

Be the first to comment!