TsinghuaC3I/MARTI
A Framework for LLM-based Multi-Agent Reinforced Training and Inference
MARTI is a framework for advanced AI developers, researchers, and engineers building multi-agent systems with Large Language Models (LLMs). It helps orchestrate multiple LLMs to collaborate on complex tasks, like code generation, by simulating their interactions and refining their strategies through reinforcement learning. Users can input a task or problem, define the roles and interactions for multiple LLM agents, and receive improved, collaboratively generated outputs.
453 stars.
Use this if you are developing or researching complex AI systems that require multiple LLMs to work together, explore solution spaces, and refine their reasoning through trial and error.
Not ideal if you are looking for an off-the-shelf, ready-to-use application for end-user tasks, or if your AI development needs are limited to single-LLM interactions.
Stars
453
Forks
46
Language
Python
License
MIT
Category
Last pushed
Feb 19, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/TsinghuaC3I/MARTI"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related models
zjunlp/KnowLM
An Open-sourced Knowledgable Large Language Model Framework.
cli99/llm-analysis
Latency and Memory Analysis of Transformer Models for Training and Inference
tanyuqian/redco
NAACL '24 (Best Demo Paper RunnerUp) / MlSys @ NeurIPS '23 - RedCoast: A Lightweight Tool to...
stanleylsx/llms_tool
一个基于HuggingFace开发的大语言模型训练、测试工具。支持各模型的webui、终端预测，低参数量及全参数模型训练(预训练、SFT、RM、PPO、DPO)和融合、量化。
slp-rl/slamkit
SlamKit is an open source tool kit for efficient training of SpeechLMs. It was used for...