AceGRPO: Adaptive Curriculum Enhanced Group Relative Policy Optimization for Autonomous Machine Learning Engineering
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866917467363737600 |
|---|---|
| author | Cai, Yuzhu Liu, Zexi Zhu, Xinyu Wang, Cheng Wang, Yanfeng Chen, Siheng |
| author_facet | Cai, Yuzhu Liu, Zexi Zhu, Xinyu Wang, Cheng Wang, Yanfeng Chen, Siheng |
| contents | Autonomous Machine Learning Engineering (MLE) requires agents to perform sustained, iterative optimization over long horizons. While recent LLM-based agents show promise, current prompt-based agents for MLE suffer from behavioral stagnation due to frozen parameters. Although Reinforcement Learning (RL) offers a remedy, applying it to MLE is hindered by prohibitive execution latency and inefficient data selection. Recognizing these challenges, we propose AceGRPO with two core components: (1) Evolving Data Buffer that continuously repurposes execution traces into reusable training tasks, and (2) Adaptive Sampling guided by a Learnability Potential function, which dynamically prioritizes tasks at the agent's learning frontier to maximize learning efficiency. Leveraging AceGRPO, our trained Ace-30B model achieves a 100% valid submission rate on MLE-Bench-Lite, approaches the performance of proprietary frontier models, and outperforms larger open-source baselines (e.g., DeepSeek-V3.2), demonstrating robust capability for sustained iterative optimization. Code is available at https://github.com/yuzhu-cai/AceGRPO. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_07906 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | AceGRPO: Adaptive Curriculum Enhanced Group Relative Policy Optimization for Autonomous Machine Learning Engineering Cai, Yuzhu Liu, Zexi Zhu, Xinyu Wang, Cheng Wang, Yanfeng Chen, Siheng Machine Learning Artificial Intelligence Autonomous Machine Learning Engineering (MLE) requires agents to perform sustained, iterative optimization over long horizons. While recent LLM-based agents show promise, current prompt-based agents for MLE suffer from behavioral stagnation due to frozen parameters. Although Reinforcement Learning (RL) offers a remedy, applying it to MLE is hindered by prohibitive execution latency and inefficient data selection. Recognizing these challenges, we propose AceGRPO with two core components: (1) Evolving Data Buffer that continuously repurposes execution traces into reusable training tasks, and (2) Adaptive Sampling guided by a Learnability Potential function, which dynamically prioritizes tasks at the agent's learning frontier to maximize learning efficiency. Leveraging AceGRPO, our trained Ace-30B model achieves a 100% valid submission rate on MLE-Bench-Lite, approaches the performance of proprietary frontier models, and outperforms larger open-source baselines (e.g., DeepSeek-V3.2), demonstrating robust capability for sustained iterative optimization. Code is available at https://github.com/yuzhu-cai/AceGRPO. |
| title | AceGRPO: Adaptive Curriculum Enhanced Group Relative Policy Optimization for Autonomous Machine Learning Engineering |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2602.07906 |