Trinity-RFT: A General-Purpose and Unified Framework for Reinforcement Fine-Tuning of Large Language Models
yanxi-chen
Abstract
Trinity-RFT is a flexible and scalable framework for reinforcement fine-tuning of large language models, supporting various interaction modes and data pipelines.
Trinity-RFT is a general-purpose, flexible and scalable framework designed for reinforcement fine-tuning (RFT) of large language models. It is built with a decoupled design, consisting of (1) an RFT-core that unifies and generalizes synchronous/asynchronous, on-policy/off-policy, and online/offline modes of RFT, (2) seamless integration for agent-environment interaction with high efficiency and robustness, and (3) systematic data pipelines optimized for RFT. Trinity-RFT can be easily adapted for diverse application scenarios, and serves as a unified platform for exploring advanced reinforcement learning paradigms. This technical report outlines the vision, features, design and implementations of Trinity-RFT, accompanied by extensive examples demonstrating the utility and user-friendliness of the proposed framework.
Community
GitHub: https://github.com/modelscope/Trinity-RFT
Documents: https://modelscope.github.io/Trinity-RFT
Trinity-RFT is currently under active development. Comments, suggestions and contributions are welcome!
This is an automated message from the Librarian Bot. I found the following papers similar to this paper.
The following papers were recommended by the Semantic Scholar API
- ActionStudio: A Lightweight Framework for Data and Training of Large Action Models (2025)
- UFT: Unifying Supervised and Reinforcement Fine-Tuning (2025)
- Reinforced MLLM: A Survey on RL-Based Reasoning in Multimodal Large Language Models (2025)
- GUI-R1 : A Generalist R1-Style Vision-Language Action Model For GUI Agents (2025)
- ARPO:End-to-End Policy Optimization for GUI Agents with Experience Replay (2025)
- MLE-Dojo: Interactive Environments for Empowering LLM Agents in Machine Learning Engineering (2025)
- Entropy-guided sequence weighting for efficient exploration in RL-based LLM fine-tuning (2025)
Please give a thumbs up to this comment if you found it helpful!
If you want recommendations for any Paper on Hugging Face checkout this Space
You can directly ask Librarian Bot for paper recommendations by tagging it in a comment:
@librarian-bot
recommend
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