pith. sign in

arxiv: 2506.03122 · v1 · pith:LYU6TUUOnew · submitted 2025-06-03 · 💻 cs.CL

AUTOCIRCUIT-RL: Reinforcement Learning-Driven LLM for Automated Circuit Topology Generation

classification 💻 cs.CL
keywords circuitdesignautocircuit-rlautomatedcircuitsefficiencyframeworksynthesis
0
0 comments X
read the original abstract

Analog circuit topology synthesis is integral to Electronic Design Automation (EDA), enabling the automated creation of circuit structures tailored to specific design requirements. However, the vast design search space and strict constraint adherence make efficient synthesis challenging. Leveraging the versatility of Large Language Models (LLMs), we propose AUTOCIRCUIT-RL,a novel reinforcement learning (RL)-based framework for automated analog circuit synthesis. The framework operates in two phases: instruction tuning, where an LLM learns to generate circuit topologies from structured prompts encoding design constraints, and RL refinement, which further improves the instruction-tuned model using reward models that evaluate validity, efficiency, and output voltage. The refined model is then used directly to generate topologies that satisfy the design constraints. Empirical results show that AUTOCIRCUIT-RL generates ~12% more valid circuits and improves efficiency by ~14% compared to the best baselines, while reducing duplicate generation rates by ~38%. It achieves over 60% success in synthesizing valid circuits with limited training data, demonstrating strong generalization. These findings highlight the framework's effectiveness in scaling to complex circuits while maintaining efficiency and constraint adherence, marking a significant advancement in AI-driven circuit design.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 2 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

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

    cs.LG 2026-03 unverdicted novelty 6.0

    ARCS generates valid SPICE-simulatable analog circuits in milliseconds via graph VAE, flow-matching, and GRPO reinforcement learning, reaching 99.9% validity with 8 evaluations across 32 topologies.

  2. pcbGPT: Automatic PCB Schematic Synthesis from Natural Language Requirements

    cs.HC 2026-05 unverdicted novelty 5.0

    pcbGPT generates KiCad schematics from natural language with 0.90 pass@1 on 20 embedded tasks via tool-augmented LLM synthesis and multi-stage validation.