mlsanityData to 14 Oct 2026

PowerGenie: Analytically-Guided Evolutionary Discovery of Superior Reconfigurable Power Converters

arXiv 2601.21984 ↗First posted 29 Jan 2026cs.LG cs.ARcited by 1

Not on the map. Why?

Abstract (arXiv)

Discovering superior circuit topologies requires navigating an exponentially large design space-a challenge traditionally reserved for human experts. Existing AI methods either select from predefined templates or generate novel topologies at a limited scale without rigorous verification, leaving large-scale performance-driven discovery underexplored. We present PowerGenie, a framework for automated discovery of higher-performance reconfigurable power converters at scale. PowerGenie introduces: (1) an automated analytical framework that determines converter functionality and theoretical performance limits without component sizing or SPICE simulation, and (2) an evolutionary finetuning method that co-evolves a generative model with its training distribution through fitness selection and uniqueness verification. Unlike existing methods that suffer from mode collapse and overfitting, our approach achieves higher syntax validity, function validity, novelty rate, and figure-of-merit (FoM). PowerGenie discovers a novel 8-mode reconfigurable converter with 23% higher FoM than the best training topology. SPICE simulations confirm average absolute efficiency gains of 10% across 8 modes and up to 17% at a single mode. Code will be released upon publication.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 22 of its 69 references that are in the map. First posted on arXiv 29 Jan 2026.

Builds on

22 of 69 references.

References · 22

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2017Proximal Policy Optimization Algorithmscited by 15,215
  3. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 8,065
  4. 2022Self-Instruct: Aligning Language Models with Self-Generated Instructionscited by 2,724
  5. 2023WizardLM: Empowering large pre-trained language models to follow complex instructionscited by 1,125
  6. 2025AlphaEvolve: A coding agent for scientific and algorithmic discoverycited by 867
  7. 2019Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Boundscited by 610
  8. 2024LESS: Selecting Influential Data for Targeted Instruction Tuningcited by 532
  9. 2023From Quantity to Quality: Boosting LLM Performance with Self-Guided Data Selection for Instruction Tuningcited by 307
  10. 2023Understanding Catastrophic Forgetting in Language Models via Implicit Inferencecited by 144
  11. 2020GCN-RL Circuit Designer: Transferable Transistor Sizing with Graph Neural Networks and Reinforcement Learningcited by 89
  12. 2024AnalogCoder: Analog Circuit Design via Training-Free Code Generationcited by 84
10 more
  1. 2023CktGNN: Circuit Graph Neural Network for Electronic Design Automationcited by 58
  2. 2025AnalogGenie: A Generative Engine for Automatic Discovery of Analog Circuit Topologiescited by 37
  3. 2024LaMAGIC: Language-Model-based Topology Generation for Analog Integrated Circuitscited by 33
  4. 2021DNN-Opt: An RL Inspired Optimization for Analog Circuit Sizing using Deep Neural Networkscited by 18
  5. 2025AnalogCoder-Pro: Unifying Analog Circuit Generation and Optimization via Multi-modal LLMscited by 15
  6. 2025AUTOCIRCUIT-RL: Reinforcement Learning-Driven LLM for Automated Circuit Topology Generationcited by 11
  7. 2023Learning to Design Analog Circuits to Meet Threshold Specificationscited by 9
  8. 2024RoSE-Opt: Robust and Efficient Analog Circuit Parameter Optimization with Knowledge-infused Reinforcement Learningcited by 9
  9. 2025LaMAGIC2: Advanced Circuit Formulations for Language Model-Based Analog Topology Generationcited by 6
  10. 2025ZeroSim: Zero-Shot Analog Circuit Evaluation with Unified Transformer Embeddingscited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Spicing up Genetic Netlist Generation with LLMscited by 0