mlsanityData to 7 Oct 2026

AnalogCoder-Pro: Unifying Analog Circuit Generation and Optimization via Multi-modal LLMs

arXiv 2508.02518 ↗First posted 4 Aug 2025cs.LGcited by 14

Not on the map. Why?

Abstract (arXiv)

Despite recent advances, analog front-end design still relies heavily on expert intuition and iterative simulations, which limits the potential for automation. We present AnalogCoder-Pro, a multimodal large language model (LLM) framework that integrates generative and optimization techniques. The framework features a multimodal diagnosis-and-repair feedback loop that uses simulation error messages and waveform images to autonomously correct design errors. It also builds a reusable circuit tool library by archiving successful designs as modular subcircuits, accelerating the development of complex systems. Furthermore, it enables end-to-end automation by generating circuit topologies from target specifications, extracting key parameters, and applying Bayesian optimization for device sizing. On a curated benchmark suite covering 13 circuit types, AnalogCoder-Pro successfully designed 28 circuits and consistently outperformed existing LLM-based methods in figures of merit.

Key facts. Cited by 14 papers in the map (data through 7 Oct 2026). Builds on 49 of its 87 references that are in the map. First posted on arXiv 4 Aug 2025.

Builds on

49 of 87 references.

References · 49

  1. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  2. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  3. 2019Optuna: A Next-generation Hyperparameter Optimization Frameworkcited by 2,455
  4. 2023Voyager: An Open-Ended Embodied Agent with Large Language Modelscited by 2,081
  5. 2023ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIscited by 1,880
  6. 2024DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligencecited by 1,154
  7. 2023CodeGeeX: A Pre-Trained Model for Code Generation with Multilingual Benchmarking on HumanEval-Xcited by 294
  8. 2023VeriGen: A Large Language Model for Verilog Code Generationcited by 197
  9. 2023ChipNeMo: Domain-Adapted LLMs for Chip Designcited by 168
  10. 2023Chip-Chat: Challenges and Opportunities in Conversational Hardware Designcited by 136
  11. 2023ChatEDA: A Large Language Model Powered Autonomous Agent for EDAcited by 118
  12. 2023ChipGPT: How far are we from natural language hardware designcited by 101
37 more
  1. 2024BetterV: Controlled Verilog Generation with Discriminative Guidancecited by 99
  2. 2023RTLFixer: Automatically Fixing RTL Syntax Errors with Large Language Modelscited by 98
  3. 2020GCN-RL Circuit Designer: Transferable Transistor Sizing with Graph Neural Networks and Reinforcement Learningcited by 89
  4. 2024AnalogCoder: Analog Circuit Design via Training-Free Code Generationcited by 82
  5. 2023AutoChip: Automating HDL Generation Using LLM Feedbackcited by 80
  6. 2023GPT4AIGChip: Towards Next-Generation AI Accelerator Design Automation via Large Language Modelscited by 59
  7. 2023CktGNN: Circuit Graph Neural Network for Electronic Design Automationcited by 55
  8. 2020AutoCkt: Deep Reinforcement Learning of Analog Circuit Designscited by 51
  9. 2024ADO-LLM: Analog Design Bayesian Optimization with In-Context Learning of Large Language Modelscited by 44
  10. 2024CraftRTL: High-quality Synthetic Data Generation for Verilog Code Models with Correct-by-Construction Non-Textual Representations and Targeted Code Repaircited by 41
  11. 2023LLM4EDA: Emerging Progress in Large Language Models for Electronic Design Automationcited by 40
  12. 2024CodeV: Empowering LLMs with HDL Generation through Multi-Level Summarizationcited by 38
  13. 2025A Survey of Research in Large Language Models for Electronic Design Automationcited by 38
  14. 2025AnalogGenie: A Generative Engine for Automatic Discovery of Analog Circuit Topologiescited by 35
  15. 2025QiMeng-CodeV-R1: Reasoning-Enhanced Verilog Generationcited by 34
  16. 2024LaMAGIC: Language-Model-based Topology Generation for Analog Integrated Circuitscited by 32
  17. 2024AmpAgent: An LLM-based Multi-Agent System for Multi-stage Amplifier Schematic Design from Literature for Process and Performance Portingcited by 29
  18. 2024Customized Retrieval Augmented Generation and Benchmarking for EDA Tool Documentation QAcited by 28
  19. 2024HDLdebugger: Streamlining HDL debugging with Large Language Modelscited by 25
  20. 2024LEDRO: LLM-Enhanced Design Space Reduction and Optimization for Analog Circuitscited by 22
  21. 2025ScaleRTL: Scaling LLMs with Reasoning Data and Test-Time Compute for Accurate RTL Code Generationcited by 22
  22. 2021DNN-Opt: An RL Inspired Optimization for Analog Circuit Sizing using Deep Neural Networkscited by 18
  23. 2024Masala-CHAI: A Large-Scale SPICE Netlist Dataset for Analog Circuits by Harnessing AIcited by 17
  24. 2024AnalogXpert: Automating Analog Topology Synthesis by Incorporating Circuit Design Expertise into Large Language Modelscited by 17
  25. 2025A Survey of Circuit Foundation Model: Foundation AI Models for VLSI Circuit Design and EDAcited by 17
  26. 2025RTL++: Graph-enhanced LLM for RTL Code Generationcited by 16
  27. 2025CircuitFusion: Multimodal Circuit Representation Learning for Agile Chip Designcited by 14
  28. 2025AMSbench: A Comprehensive Benchmark for Evaluating MLLM Capabilities in AMS Circuitscited by 14
  29. 2025Divergent Thoughts toward One Goal: LLM-based Multi-Agent Collaboration System for Electronic Design Automationcited by 12
  30. 2024LLM-Enhanced Bayesian Optimization for Efficient Analog Layout Constraint Generationcited by 11
  31. 2024Natural language is not enough: Benchmarking multi-modal generative AI for Verilog generationcited by 11
  32. 2024SPICEPilot: Navigating SPICE Code Generation and Simulation with AI Guidancecited by 10
  33. 2025AUTOCIRCUIT-RL: Reinforcement Learning-Driven LLM for Automated Circuit Topology Generationcited by 10
  34. 2024INSIGHT: Universal Neural Simulator for Analog Circuits Harnessing Autoregressive Transformerscited by 8
  35. 2025LaMAGIC2: Advanced Circuit Formulations for Language Model-Based Analog Topology Generationcited by 6
  36. 2025MMCircuitEval: A Comprehensive Multimodal Circuit-Focused Benchmark for Evaluating LLMscited by 6
  37. 2025Evaluating LLM-based Workflows for Switched-Mode Power Supply Designcited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 3; 2026: 11.

14 papers.

Sort:

By area:

  1. 2025HeaRT: A Hierarchical Circuit Reasoning Tree-Based Agentic Framework for AMS Design Optimizationcited by 5
  2. 2026AutoSizer: Automatic Sizing of Analog and Mixed-Signal Circuits via Large Language Model (LLM) Agentscited by 4
  3. 2026OSIRIS: Bridging Analog Circuit Design and Machine Learning with Scalable Dataset Generationcited by 2
  4. 2026CircuitFormer: A Circuit Language Model for Analog Topology Design from Natural Language Promptcited by 2
  5. 2025Dataset Construction for Training LLM to Learn Analog Circuit Knowledgecited by 1
  6. 2025Combining Large Language Models and Gradient-Free Optimization for Automatic Control Policy Synthesiscited by 1
  7. 2026PowerGenie: Analytically-Guided Evolutionary Discovery of Superior Reconfigurable Power Converterscited by 1
  8. 2026AstRL: Analog and Mixed-Signal Circuit Synthesis with Deep Reinforcement Learningcited by 1
  9. 2026SABLE: An NDA-Safe Closed-Loop LLM Framework for Analog Circuit Optimization in Industrial EDA Flowscited by 1
  10. 2026Agentic Electronic Design Automation: A Handoff Perspectivecited by 0
  11. 2026EXPLORE: Exploration with Guided Search for Analog Topology Generation using Language Modelscited by 0
  12. 2026AaLLM: An End-to-End Analog Circuit Design Framework from Topology Generation to Sizing Using Large Language Modelscited by 0
2 more
  1. 2026EngIntervene: Benchmarking Multimodal Engineering State Understanding and Design Intervention Reasoningcited by 0
  2. 2026Long-Horizon Analog Design Bench: Benchmarking Agents on Hours-Long Analog and Mixed-Signal Circuit Design Taskscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026AnalogAgent: Self-Improving Analog Circuit Design Automation with LLM Agents
  2. 2024CktGen: Automated Analog Circuit Design with Generative Artificial Intelligence
  3. 2025White-Box Reasoning: Synergizing LLM Strategy and gm/Id Data for Automated Analog Circuit Design
  4. 2025EEschematic: Multimodal-LLM Based AI Agent for Schematic Generation of Analog Circuit
  5. 2025AnalogSAGE: Self-evolving Analog Design Multi-Agents with Stratified Memory and Grounded Experience
  6. 2025CIRCUIT: A Benchmark for Circuit Interpretation and Reasoning Capabilities of LLMs
  7. 2026Simulation-Aware In-Context Policy Improvement for LLM-Aided Analog Layout Refinement
  8. 2026AgenticSizing: A Large Language Model-based Multi-Agent Framework for Analog Circuit Sizing