OpenTinker: Separating Concerns in Agentic Reinforcement Learning
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_ | 1866911369144565760 |
|---|---|
| author | Zhu, Siqi You, Jiaxuan |
| author_facet | Zhu, Siqi You, Jiaxuan |
| contents | We introduce OpenTinker, an infrastructure for reinforcement learning (RL) of large language model (LLM) agents built around a separation of concerns across algorithm design, execution, and agent-environment interaction. Rather than relying on monolithic, end-to-end RL pipelines, OpenTinker decomposes agentic learning systems into lightweight, composable components with clearly defined abstraction boundaries. Users specify agents, environments, and interaction protocols, while inference and training are delegated to a managed execution runtime. OpenTinker introduces a centralized scheduler for managing training and inference workloads, including LoRA-based and full-parameter RL, supervised fine-tuning, and inference, over shared resources. We further discuss design principles for extending OpenTinker to multi-agent training. Finally, we present a set of RL use cases that demonstrate the effectiveness of the framework in practical agentic learning scenarios. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_07376 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | OpenTinker: Separating Concerns in Agentic Reinforcement Learning Zhu, Siqi You, Jiaxuan Artificial Intelligence Distributed, Parallel, and Cluster Computing We introduce OpenTinker, an infrastructure for reinforcement learning (RL) of large language model (LLM) agents built around a separation of concerns across algorithm design, execution, and agent-environment interaction. Rather than relying on monolithic, end-to-end RL pipelines, OpenTinker decomposes agentic learning systems into lightweight, composable components with clearly defined abstraction boundaries. Users specify agents, environments, and interaction protocols, while inference and training are delegated to a managed execution runtime. OpenTinker introduces a centralized scheduler for managing training and inference workloads, including LoRA-based and full-parameter RL, supervised fine-tuning, and inference, over shared resources. We further discuss design principles for extending OpenTinker to multi-agent training. Finally, we present a set of RL use cases that demonstrate the effectiveness of the framework in practical agentic learning scenarios. |
| title | OpenTinker: Separating Concerns in Agentic Reinforcement Learning |
| topic | Artificial Intelligence Distributed, Parallel, and Cluster Computing |
| url | https://arxiv.org/abs/2601.07376 |