mlsanityData to 14 Oct 2026

HeaRT: A Hierarchical Circuit Reasoning Tree-Based Agentic Framework for AMS Design Optimization

arXiv 2511.19669 ↗First posted 24 Nov 2025cs.AIcited by 5

On the map: LLM agents and tool use → Software engineering coding agents

Abstract (arXiv)

Conventional AI-driven AMS design automation algorithms remain constrained by their reliance on high-quality datasets to capture underlying circuit behavior, coupled with poor transferability across architectures, and a lack of adaptive mechanisms. This work proposes HeaRT, a hierarchical circuit reasoning-based agentic framework for automation loops and a step toward adaptive, human-style design optimization. HeaRT consistently improves F1(subcircuits) by >= 13.5% and F1(loops) by >= 37.8% over few-shot prompting baselines across multiple LLM backbones on our 40-circuit AMS benchmark of flattened SPICE netlists, even as circuit complexity increases. Our experiments further show that HeaRT achieves >= 3x faster convergence in incremental design adaptation tasks under specification shifts across diverse optimization approaches, supporting both topology reconfiguration and sizing.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use. Builds on 41 of its 77 references that are in the map. First posted on arXiv 24 Nov 2025.

Builds on

41 of 77 references.

Closest ancestors · 1

Same direction, newest first

  1. 2025EEsizer: LLM-Based AI Agent for Sizing of Analog and Mixed Signal Circuit29 Sep

Other references · 40

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2024The Llama 3 Herd of Modelscited by 14,715
  3. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  4. 2016Overcoming catastrophic forgetting in neural networkscited by 4,787
  5. 2024GPT-4o System Cardcited by 4,588
  6. 2025Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilitiescited by 3,796
  7. 2023A Survey on Large Language Model based Autonomous Agentscited by 2,242
  8. 2023A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questionscited by 1,601
  9. 2023The Rise and Potential of Large Language Model Based Agents: A Surveycited by 1,439
  10. 2025Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Modelscited by 384
  11. 2019Scalable Global Optimization via Local Bayesian Optimizationcited by 374
  12. 2025Towards Large Reasoning Models: A Survey of Reinforced Reasoning with Large Language Modelscited by 293
28 more
  1. 2025Agentic Reasoning: A Streamlined Framework for Enhancing LLM Reasoning with Agentic Toolscited by 106
  2. 2024LLMOPT: Learning to Define and Solve General Optimization Problems from Scratchcited by 102
  3. 2020GCN-RL Circuit Designer: Transferable Transistor Sizing with Graph Neural Networks and Reinforcement Learningcited by 89
  4. 2023Think Twice: Perspective-Taking Improves Large Language Models' Theory-of-Mind Capabilitiescited by 89
  5. 2024AnalogCoder: Analog Circuit Design via Training-Free Code Generationcited by 84
  6. 2022Recent Advances in Bayesian Optimizationcited by 76
  7. 2020AutoCkt: Deep Reinforcement Learning of Analog Circuit Designscited by 51
  8. 2024ADO-LLM: Analog Design Bayesian Optimization with In-Context Learning of Large Language Modelscited by 44
  9. 2023Achieving a Better Stability-Plasticity Trade-off via Auxiliary Networks in Continual Learningcited by 41
  10. 2025AnalogGenie: A Generative Engine for Automatic Discovery of Analog Circuit Topologiescited by 37
  11. 2024Data is all you need: Finetuning LLMs for Chip Design via an Automated design-data augmentation frameworkcited by 36
  12. 2025Semantic-Aware Logical Reasoning via a Semiotic Frameworkcited by 32
  13. 2024LEDRO: LLM-Enhanced Design Space Reduction and Optimization for Analog Circuitscited by 22
  14. 2021DNN-Opt: An RL Inspired Optimization for Analog Circuit Sizing using Deep Neural Networkscited by 18
  15. 2024AnalogXpert: Automating Analog Topology Synthesis by Incorporating Circuit Design Expertise into Large Language Modelscited by 18
  16. 2025AnalogCoder-Pro: Unifying Analog Circuit Generation and Optimization via Multi-modal LLMscited by 15
  17. 2021An Efficient Batch Constrained Bayesian Optimization Approach for Analog Circuit Synthesis via Multi-objective Acquisition Ensemblecited by 13
  18. 2024Schemato -- An LLM for Netlist-to-Schematic Conversioncited by 11
  19. 2024RoSE-Opt: Robust and Efficient Analog Circuit Parameter Optimization with Knowledge-infused Reinforcement Learningcited by 9
  20. 2025MenTeR: A fully-automated Multi-agenT workflow for end-to-end RF/Analog Circuits Netlist Designcited by 7
  21. 2025Image2Net: Datasets, Benchmark and Hybrid Framework to Convert Analog Circuit Diagrams into Netlistscited by 7
  22. 2022RobustAnalog: Fast Variation-Aware Analog Circuit Design Via Multi-task RLcited by 5
  23. 2025AnalogTester: A Large Language Model-Based Framework for Automatic Testbench Generation in Analog Circuit Designcited by 4
  24. 2022Automated Circuit Sizing with Multi-objective Optimization based on Differential Evolution and Bayesian Inferencecited by 3
  25. 2020A Functional Block Decomposition Method for Automatic Op-Amp Designcited by 2
  26. 2025GENIE-ASI: Generative Instruction and Executable Code for Analog Subcircuit Identificationcited by 2
  27. 2023Practical Layout-Aware Analog/Mixed-Signal Design Automation with Bayesian Neural Networkscited by 1
  28. 2025Thinking with Many Minds: Using Large Language Models for Multi-Perspective Problem-Solvingcited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 4.

5 papers.

  1. 2025When Forgetting Builds Reliability: LLM Unlearning for Reliable Hardware Code Generationcited by 1
  2. 2026Complexity Horizons of Compressed Models in Analog Circuit Analysiscited by 0
  3. 2026Towards Reliable AI-Assisted Analog Design: Template-Constrained LLM Agents for SAR ADC Generationcited by 0
  4. 2026Analog-DB: An Agent-First Analog Integrated Circuit Database, From Blocks to Systemscited by 0
  5. 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. 2025AMS-IO-Bench and AMS-IO-Agent: Benchmarking and Structured Reasoning for Analog and Mixed-Signal Integrated Circuit Input/Output Design
  2. 2026RFChipAgent: Multi-Agentic AI Flow for Analog/RF Chip Design
  3. 2025ORFS-agent: Tool-Using Agents for Chip Design Optimization
  4. 2025TopoSizing: An LLM-aided Framework of Topology-based Understanding and Sizing for AMS Circuits
  5. 2026AutoSizer: Automatic Sizing of Analog and Mixed-Signal Circuits via Large Language Model (LLM) Agents
  6. 2026AaLLM: An End-to-End Analog Circuit Design Framework from Topology Generation to Sizing Using Large Language Models
  7. 2024AMSnet-KG: A Netlist Dataset for LLM-based AMS Circuit Auto-Design Using Knowledge Graph RAG
  8. 2026AnalogAgent: Self-Improving Analog Circuit Design Automation with LLM Agents