Update README.md
Browse files
README.md
CHANGED
|
@@ -5,8 +5,10 @@ colorFrom: green
|
|
| 5 |
colorTo: gray
|
| 6 |
sdk: static
|
| 7 |
pinned: false
|
|
|
|
| 8 |
---
|
| 9 |
|
|
|
|
| 10 |
MLE-Dojo is a Gym-style framework for systematically training, evaluating, and improving autonomous large language model (LLM) agents in iterative machine learning engineering (MLE) workflows.
|
| 11 |
Unlike existing benchmarks that primarily rely on static datasets or single-attempt evaluations, MLE-Dojo provides an interactive environment enabling agents to iteratively experiment, debug, and refine solutions through structured feedback loops. Built upon 200+ real-world Kaggle challenges (e.g., tabular data analysis, computer vision, natural language processing, and time series forecasting). MLE-Dojo covers diverse, open-ended MLE tasks carefully curated to reflect realistic engineering scenarios such as data processing, architecture search, hyperparameter tuning, and code debugging.
|
| 12 |
Its fully executable environment supports comprehensive agent training via both supervised fine-tuning and reinforcement learning, facilitating iterative experimentation, realistic data sampling, and real-time outcome verification.
|
|
|
|
| 5 |
colorTo: gray
|
| 6 |
sdk: static
|
| 7 |
pinned: false
|
| 8 |
+
paper: https://arxiv.org/abs/2505.07782
|
| 9 |
---
|
| 10 |
|
| 11 |
+
|
| 12 |
MLE-Dojo is a Gym-style framework for systematically training, evaluating, and improving autonomous large language model (LLM) agents in iterative machine learning engineering (MLE) workflows.
|
| 13 |
Unlike existing benchmarks that primarily rely on static datasets or single-attempt evaluations, MLE-Dojo provides an interactive environment enabling agents to iteratively experiment, debug, and refine solutions through structured feedback loops. Built upon 200+ real-world Kaggle challenges (e.g., tabular data analysis, computer vision, natural language processing, and time series forecasting). MLE-Dojo covers diverse, open-ended MLE tasks carefully curated to reflect realistic engineering scenarios such as data processing, architecture search, hyperparameter tuning, and code debugging.
|
| 14 |
Its fully executable environment supports comprehensive agent training via both supervised fine-tuning and reinforcement learning, facilitating iterative experimentation, realistic data sampling, and real-time outcome verification.
|