# ARCS: Autoregressive Circuit Synthesis with Topology-Aware Graph Attention and Spec Conditioning

Source: [ARCS: Autoregressive Circuit Synthesis with Topology-Aware Graph Attention and Spec Conditioning](<https://www.sota2.com/research/paper/69cca67a0636e5bf4afcbaf1>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-04-22T05:22:24.043Z

Authors: Tushar Dhananjay Pathak

Published: 2026-03-30T23:14:08.000Z

## Abstract

This paper presents ARCS (Autoregressive Circuit Synthesis), a system for amortized analog circuit generation. ARCS produces complete, SPICE-simulatable designs (topology and component values) in milliseconds rather than the minutes required by search-based methods. A hybrid pipeline combines two learned generators, a graph VAE and a flow-matching model, with SPICE-based ranking. It achieves 99.9% simulation validity (reward 6.43/8.0) across 32 topologies using only 8 SPICE evaluations, 40x fewer than genetic algorithms. For single-model inference, a topology-aware Graph Transformer with Best-of-3 candidate selection reaches 85% simulation validity in 97ms, over 600x faster than random search. The key technical contribution adapts Group Relative Policy Optimization (GRPO) to multi-topology circuit reinforcement learning. GRPO resolves a critical failure mode of REINFORCE, cross-topology reward distribution mismatch, through per-topology advantage normalization. This improves simulation validity by +9.6 percentage points over REINFORCE in only 500 RL steps (10x fewer). Grammar-constrained decoding additionally guarantees 100% structural validity by construction via topology-aware token masking.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Generative circuit design on Analog board-level circuit design templates](<https://www.sota2.com/research/sota/generative-circuit-design-on-analog-board-level-circuit-design-templates.md>): Generative circuit design; Analog board-level circuit design templates; Generation Time (s): 0.02.

- [Circuit Design Generation on 32 circuit topologies (publication evaluation)](<https://www.sota2.com/research/sota/circuit-design-generation-on-32-circuit-topologies-publication-evaluation.md>): Circuit Design Generation; 32 circuit topologies (publication evaluation); Reward: 6.43.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2603.29068>)

[PDF](<https://arxiv.org/pdf/2603.29068.pdf>)
