AIDE: AI-Driven Exploration in the Space of Code
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866915159238246400 |
|---|---|
| author | Jiang, Zhengyao Schmidt, Dominik Srikanth, Dhruv Xu, Dixing Kaplan, Ian Jacenko, Deniss Wu, Yuxiang |
| author_facet | Jiang, Zhengyao Schmidt, Dominik Srikanth, Dhruv Xu, Dixing Kaplan, Ian Jacenko, Deniss Wu, Yuxiang |
| contents | Machine learning, the foundation of modern artificial intelligence, has driven innovations that have fundamentally transformed the world. Yet, behind advancements lies a complex and often tedious process requiring labor and compute intensive iteration and experimentation. Engineers and scientists developing machine learning models spend much of their time on trial-and-error tasks instead of conceptualizing innovative solutions or research hypotheses. To address this challenge, we introduce AI-Driven Exploration (AIDE), a machine learning engineering agent powered by large language models (LLMs). AIDE frames machine learning engineering as a code optimization problem, and formulates trial-and-error as a tree search in the space of potential solutions. By strategically reusing and refining promising solutions, AIDE effectively trades computational resources for enhanced performance, achieving state-of-the-art results on multiple machine learning engineering benchmarks, including our Kaggle evaluations, OpenAI MLE-Bench and METRs RE-Bench. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_13138 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | AIDE: AI-Driven Exploration in the Space of Code Jiang, Zhengyao Schmidt, Dominik Srikanth, Dhruv Xu, Dixing Kaplan, Ian Jacenko, Deniss Wu, Yuxiang Artificial Intelligence Machine Learning Machine learning, the foundation of modern artificial intelligence, has driven innovations that have fundamentally transformed the world. Yet, behind advancements lies a complex and often tedious process requiring labor and compute intensive iteration and experimentation. Engineers and scientists developing machine learning models spend much of their time on trial-and-error tasks instead of conceptualizing innovative solutions or research hypotheses. To address this challenge, we introduce AI-Driven Exploration (AIDE), a machine learning engineering agent powered by large language models (LLMs). AIDE frames machine learning engineering as a code optimization problem, and formulates trial-and-error as a tree search in the space of potential solutions. By strategically reusing and refining promising solutions, AIDE effectively trades computational resources for enhanced performance, achieving state-of-the-art results on multiple machine learning engineering benchmarks, including our Kaggle evaluations, OpenAI MLE-Bench and METRs RE-Bench. |
| title | AIDE: AI-Driven Exploration in the Space of Code |
| topic | Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2502.13138 |