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

arXiv: https://arxiv.org/abs/2607.05704 · HTML: https://mlsanity.com/paper/2607.05704/

## 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 (most cited first, 21 of 21)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [Optuna: A Next-generation Hyperparameter Optimization Framework](https://mlsanity.com/paper/1907.10902/) (2019)
- [DARTS: Differentiable Architecture Search](https://mlsanity.com/paper/1806.09055/) (2018)
- [Neural Architecture Search with Reinforcement Learning](https://mlsanity.com/paper/1611.01578/) (2016)
- [Competition-Level Code Generation with AlphaCode](https://mlsanity.com/paper/2203.07814/) (2022)
- [What Makes Good In-Context Examples for GPT-3?](https://mlsanity.com/paper/2101.06804/) (2021)
- [Regularized Evolution for Image Classifier Architecture Search](https://mlsanity.com/paper/1802.01548/) (2018)
- [Large Language Models as Optimizers](https://mlsanity.com/paper/2309.03409/) (2023)
- [Hyperband: A Novel Bandit-Based Approach to Hyperparameter Optimization](https://mlsanity.com/paper/1603.06560/) (2016)
- [Learning To Retrieve Prompts for In-Context Learning](https://mlsanity.com/paper/2112.08633/) (2021)
- [LLMatic: Neural Architecture Search via Large Language Models and Quality Diversity Optimization](https://mlsanity.com/paper/2306.01102/) (2023)
- [Best Practices for Scientific Research on Neural Architecture Search](https://mlsanity.com/paper/1909.02453/) (2019)
- [Optuna vs Code Llama: Are LLMs a New Paradigm for Hyperparameter Tuning?](https://mlsanity.com/paper/2504.06006/) (2025)
- [LEMUR Neural Network Dataset: Towards Seamless AutoML](https://mlsanity.com/paper/2504.10552/) (2025)
- [Enhancing LLM-Based Neural Network Generation: Few-Shot Prompting and Efficient Validation for Automated Architecture Design](https://mlsanity.com/paper/2512.24120/) (2025)
- [Resource-Efficient Iterative LLM-Based NAS with Feedback Memory](https://mlsanity.com/paper/2603.12091/) (2026)

## 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.