AMAP-ML/Tree-GRPO

[ICLR 2026] Tree Search for LLM Agent Reinforcement Learning

Really freeApache-2.0Python

Stars: 407
Forks: 41
Open issues: 4
Last push: 8mo ago

About Tree-GRPO

Tree-GRPO is a free, open-source LLM chat app by AMAP-ML, written mainly in Python. [ICLR 2026] Tree Search for LLM Agent Reinforcement Learning. It has 407 GitHub stars and 41 forks, and was last updated 8mo ago. It's released under the Apache-2.0 license, a standard open-source license.

License: Apache-2.0
Language: Python
Stars: 407
Last update: 8mo ago
Runs on Mac: Not stated
GPU: Not stated
Paid API key: Not required
Self-hostable: Yes

Similar free tools

All LLMs & chat tools →

Tree-GRPO FAQ

Is Tree-GRPO free?

Yes. Tree-GRPO is open source and free to use. It's released under the Apache-2.0 license, a standard open-source license.

Does Tree-GRPO run on a Mac?

The project doesn't say. Check its installation guide before you start.

Does Tree-GRPO need a GPU?

The project doesn't state hardware needs. AI models generally run much faster with a GPU.

Is Tree-GRPO still maintained?

It was last updated 8mo ago. Check recent issues on GitHub to judge how active it is.

What are alternatives to Tree-GRPO?

Similar free, open-source tools include Hands-On-Large-Language-Models, FinGPT, Qwen, OpenRLHF.

Related topics

agent llm reinforcement-learning tree large-language-model language model tree grpo