mlsanityData to 14 Oct 2026

Curating Same-Family Neural Networks for LLM-Guided Model Improvement: A Controlled Case Study

arXiv 2607.05704 ↗First posted 6 Jul 2026cs.LG cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Neural-network repositories contain executable models, recipes, input transformations, and measured accuracies. We study whether one same-family experiment can be curated as prompt guidance for LLM-based improvement of a low-performing target under equal generation and evaluation budgets. TuneNNGen extends NNGPT with a source-guided route and compares it with target-only generation on one CIFAR-10 target, two fixed source-selection rules, three code LLMs, and an additional SVHN target. Under the historical one-epoch search protocol, best-of-budget accuracy on the available evaluation split rises from 23.98% to 50.49% on CIFAR-10 and from 22.54% to 78.80% on SVHN. Selected five-epoch, three-seed means on train-derived validation splits retain gains of 40.94 points on CIFAR-10, 18.83 on Imagenette, and 7.27 on CIFAR-100. Direct-copy and negative-control analyses show that gains depend on source-target compatibility and LLM adaptation; stored source accuracy alone does not predict transferability.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 21 of its 26 references that are in the map. First posted on arXiv 6 Jul 2026.

Builds on

21 of 26 references.

References · 21

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  3. 2021Evaluating Large Language Models Trained on Codecited by 8,320
  4. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,442
  5. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,276
  6. 2023Self-Refine: Iterative Refinement with Self-Feedbackcited by 3,442
  7. 2019Optuna: A Next-generation Hyperparameter Optimization Frameworkcited by 2,501
  8. 2018DARTS: Differentiable Architecture Searchcited by 1,798
  9. 2016Neural Architecture Search with Reinforcement Learningcited by 1,499
  10. 2022Competition-Level Code Generation with AlphaCodecited by 1,462
  11. 2021What Makes Good In-Context Examples for GPT-3?cited by 1,195
  12. 2018Regularized Evolution for Image Classifier Architecture Searchcited by 909
9 more
  1. 2023Large Language Models as Optimizerscited by 864
  2. 2016Hyperband: A Novel Bandit-Based Approach to Hyperparameter Optimizationcited by 699
  3. 2021Learning To Retrieve Prompts for In-Context Learningcited by 648
  4. 2023LLMatic: Neural Architecture Search via Large Language Models and Quality Diversity Optimizationcited by 87
  5. 2019Best Practices for Scientific Research on Neural Architecture Searchcited by 54
  6. 2025Optuna vs Code Llama: Are LLMs a New Paradigm for Hyperparameter Tuning?cited by 21
  7. 2025LEMUR Neural Network Dataset: Towards Seamless AutoMLcited by 20
  8. 2025Enhancing LLM-Based Neural Network Generation: Few-Shot Prompting and Efficient Validation for Automated Architecture Designcited by 10
  9. 2026Resource-Efficient Iterative LLM-Based NAS with Feedback Memorycited by 7

Built on by

Not cited yet.