CircuitFormer: A Circuit Language Model for Analog Topology Design from Natural Language Prompt

• URL: http://arxiv.org/abs/2605.05773v1
• Date: Thu, 07 May 2026 07:04:36 GMT
• Title: CircuitFormer: A Circuit Language Model for Analog Topology Design from Natural Language Prompt
• Abstract summary: We present the largest annotated dataset of analog circuit netlists to date, comprising 31,341 netlist-natural language description pairs.<n>We also propose Circuit Tokenizer (CKT), a novel circuit graph tokenizer designed to encode netlist connectivity by explicitly mining frequent subcircuits.
• Score: 2.9943388961167705
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Automating analog circuit design remains a longstanding challenge in Electronic Design Automation (EDA). While Transformer-based Large Language Models (LLMs) have revolutionized software code generation, their application to analog hardware design is hindered by two critical limitations: (i) the scarcity of analog design datasets containing natural language description of a design and its corresponding netlist, and (ii) the inefficiency of general-purpose tokenizers (e.g., Byte Pair Encoding (BPE)) in capturing the inherent graph structure of circuits. To bridge this gap, first, we curate the largest annotated dataset of analog circuit netlists to date, comprising 31,341 netlist-natural language description pairs across all major circuit classes. Furthermore, we propose Circuit Tokenizer (CKT), a novel circuit graph tokenizer designed to encode netlist connectivity by explicitly mining frequent subcircuits. In terms of scalability, CKT overcomes the bottleneck of prior circuit graph serialization methods where vocabulary size scales linearly with maximum number of components in the dataset, n_max, (O(n_max)); instead, CKT decouples vocabulary growth from circuit complexity, achieving a constant O(1) complexity. Empirically, CKT outperforms standard BPE on circuit topology representation, reducing sequence length by 57% and achieving a 2.3x superior compression ratio using a compact, fixed vocabulary of size 512. Leveraging this optimized tokenization, we train a circuit-specific language model, CircuitFormer, a 511M parameter encoder-decoder transformer. Our model achieves 100% syntactic correctness and an 83% functional success rate across all major analog circuit categories, outperforming state-of-the-art open-source LLMs by 10% and 14%, respectively, while requiring 240x fewer parameters. The dataset is publicly available at https://huggingface.co/datasets/touhid314/cktformer-dataset.

Related papers

• Fast correlated decoding of transversal logical algorithms [67.01652927671279]
  Quantum error correction (QEC) is required for large-scale computation, but incurs a significant resource overhead.<n>Recent advances have shown that by jointly decoding logical qubits in algorithms composed of logical gates, the number of syndrome extraction rounds can be reduced.<n>Here, we reform the problem of decoding circuits by directly decoding relevant logical operator products as they propagate through the circuit.
  arXiv  Detail & Related papers  (2025-05-19T18:00:00Z)
• Systems and Algorithms for Convolutional Multi-Hybrid Language Models at Scale [68.6602625868888]
  We introduce convolutional multi-hybrid architectures, with a design grounded on two simple observations.<n>Operators in hybrid models can be tailored to token manipulation tasks such as in-context recall, multi-token recall, and compression.<n>We train end-to-end 1.2 to 2.9 times faster than optimized Transformers, and 1.1 to 1.4 times faster than previous generation hybrids.
  arXiv  Detail & Related papers  (2025-02-25T19:47:20Z)
• Architect of the Bits World: Masked Autoregressive Modeling for Circuit Generation Guided by Truth Table [5.300504429005315]
  We propose a novel approach integrating conditional generative models with differentiable architecture search (DAS) for circuit generation.<n>Our approach first introduces CircuitVQ, a circuit tokenizer trained based on our Circuit AutoEncoder.<n>We then develop CircuitAR, a masked autoregressive model leveraging CircuitVQ as the tokenizer.
  arXiv  Detail & Related papers  (2025-02-18T11:13:03Z)
• Position-aware Automatic Circuit Discovery [59.64762573617173]
  We identify a gap in existing circuit discovery methods, treating model components as equally relevant across input positions.<n>We propose two improvements to incorporate positionality into circuits, even on tasks containing variable-length examples.<n>Our approach enables fully automated discovery of position-sensitive circuits, yielding better trade-offs between circuit size and faithfulness compared to prior work.
  arXiv  Detail & Related papers  (2025-02-07T00:18:20Z)
• Supervised Learning for Analog and RF Circuit Design: Benchmarks and Comparative Insights [10.354863964933019]
  This study explores supervised ML-based approaches for designing circuit parameters from performance specifications across various circuit types.<n>Our results show that simpler circuits, such as low-noise amplifiers, achieve exceptional accuracy with mean relative errors as low as 0.3%.<n>For heterogeneous circuits, our approach achieves an 88% reduction in errors with increased training data, with the receiver achieving a mean relative error as low as 0.23%.
  arXiv  Detail & Related papers  (2025-01-21T02:48:23Z)
• AICircuit: A Multi-Level Dataset and Benchmark for AI-Driven Analog Integrated Circuit Design [10.354863964933019]
  We present AICircuit, a benchmark for developing and evaluating machine learning algorithms in analog and radio-frequency circuit design. A major obstacle for bearing the power of machine learning in circuit design is the availability of a generic and diverse dataset. We extensively evaluate various ML algorithms on the dataset, revealing the potential of ML algorithms in learning the mapping from the design specifications to the desired circuit parameters.
  arXiv  Detail & Related papers  (2024-07-22T20:32:16Z)
• LaMAGIC: Language-Model-based Topology Generation for Analog Integrated Circuits [17.002169206594793]
  We introduce LaMAGIC, a pioneering language model-based topology generation model. LaMAGIC can efficiently generate an optimized circuit design from the custom specification in a single pass. LaMAGIC achieves a success rate of up to 96% under a strict tolerance of 0.01.
  arXiv  Detail & Related papers  (2024-07-19T22:51:41Z)
• Circuit Transformer: A Transformer That Preserves Logical Equivalence [20.8279111910994]
  We introduce a generative neural model, the "Circuit Transformer", which produces logic circuits strictly equivalent to given Boolean functions.<n>A Markov decision process formulation is also proposed for optimizing certain objectives of circuits.
  arXiv  Detail & Related papers  (2024-03-14T03:24:14Z)
• CktGNN: Circuit Graph Neural Network for Electronic Design Automation [67.29634073660239]
  This paper presents a Circuit Graph Neural Network (CktGNN) that simultaneously automates the circuit topology generation and device sizing. We introduce Open Circuit Benchmark (OCB), an open-sourced dataset that contains $10$K distinct operational amplifiers. Our work paves the way toward a learning-based open-sourced design automation for analog circuits.
  arXiv  Detail & Related papers  (2023-08-31T02:20:25Z)
• Pretraining Graph Neural Networks for few-shot Analog Circuit Modeling and Design [68.1682448368636]
  We present a supervised pretraining approach to learn circuit representations that can be adapted to new unseen topologies or unseen prediction tasks. To cope with the variable topological structure of different circuits we describe each circuit as a graph and use graph neural networks (GNNs) to learn node embeddings. We show that pretraining GNNs on prediction of output node voltages can encourage learning representations that can be adapted to new unseen topologies or prediction of new circuit level properties.
  arXiv  Detail & Related papers  (2022-03-29T21:18:47Z)
• Non-Autoregressive Transformer ASR with CTC-Enhanced Decoder Input [54.82369261350497]
  We propose a CTC-enhanced NAR transformer, which generates target sequence by refining predictions of the CTC module. Experimental results show that our method outperforms all previous NAR counterparts and achieves 50x faster decoding speed than a strong AR baseline with only 0.0 0.3 absolute CER degradation on Aishell-1 and Aishell-2 datasets.
  arXiv  Detail & Related papers  (2020-10-28T15:00:09Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.