Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2604.26211 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910176229982208 |
|---|---|
| author | Nixon, Jeremy Singh, Annika |
| author_facet | Nixon, Jeremy Singh, Annika |
| contents | In order to automate AI research we introduce a full, end-to-end framework, OMEGA: Optimizing Machine learning by Evaluating Generated Algorithms, that starts at idea generation and ends with executable code. Our system combines structured meta-prompt engineering with executable code generation to create new ML classifiers. The OMEGA framework has been utilized to generate several novel algorithms that outperform scikit-learn baselines across a robust selection of 20 benchmark datasets (infinity-bench). You can access models discussed in this paper and more in the python package: pip install omega-models. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_26211 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | OMEGA: Optimizing Machine Learning by Evaluating Generated Algorithms Nixon, Jeremy Singh, Annika Artificial Intelligence Machine Learning In order to automate AI research we introduce a full, end-to-end framework, OMEGA: Optimizing Machine learning by Evaluating Generated Algorithms, that starts at idea generation and ends with executable code. Our system combines structured meta-prompt engineering with executable code generation to create new ML classifiers. The OMEGA framework has been utilized to generate several novel algorithms that outperform scikit-learn baselines across a robust selection of 20 benchmark datasets (infinity-bench). You can access models discussed in this paper and more in the python package: pip install omega-models. |
| title | OMEGA: Optimizing Machine Learning by Evaluating Generated Algorithms |
| topic | Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2604.26211 |