OpenTinker: Separating Concerns in Agentic Reinforcement Learning
Abstract
OpenTinker provides a modular infrastructure for reinforcement learning of large language model agents with separated components and managed execution runtime.
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.
Community
🎉 Introducing OpenTinker
🚀 A scalable RL infrastructure for LLM agents that separates what you build (agents + environments) from how it runs (training + inference)!
🧩 Composable RL-as-a-Service
No more monolithic RL pipelines. OpenTinker decomposes agentic learning into lightweight, modular components with clean abstraction boundaries. Plug in new agents, environments, and interaction protocols with minimal friction.
⚙️ Unified Runtime for Training + Inference
A centralized scheduler manages shared compute across workloads like RL (LoRA / full-parameter), SFT, and high-throughput inference. Built for multi-tenant scaling and real-world iteration speed.
🤖 Multi-Agent Ready by Design
OpenTinker supports coordinator-driven multi-agent interaction. Each agent can optimize independently while coordination emerges through environment dynamics. This keeps MARL scalable, flexible, and system-friendly.
🔗 Links:
📄 Paper (arXiv): https://arxiv.org/pdf/2601.07376
💻 GitHub: https://github.com/open-tinker/OpenTinker
Models citing this paper 0
No model linking this paper
Datasets citing this paper 0
No dataset linking this paper
Spaces citing this paper 0
No Space linking this paper
Collections including this paper 0
No Collection including this paper