FareedKhan-dev/multi-agent-training-grpo
A multi-agent system trained with GRPO for reliable long-horizon task planning and execution.
This project helps AI developers build more reliable multi-agent systems that can tackle complex, long-term tasks without going "off track" or producing incorrect information. It takes a description of a long-horizon task and various sub-agents as input, then outputs a robust, trained multi-agent system capable of accurate planning and execution. AI developers who build or integrate advanced AI agents into larger systems would find this particularly useful.
Use this if you are developing multi-agent AI systems for complex, multi-step tasks and need to reduce errors, hallucinations, and improve overall planning and execution reliability.
Not ideal if you are looking for a pre-trained, off-the-shelf solution for simple, single-step AI tasks or if you are not an AI developer.
Stars
22
Forks
6
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Feb 09, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/rag/FareedKhan-dev/multi-agent-training-grpo"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
deepsense-ai/ragbits
Building blocks for rapid development of GenAI applications
infiniflow/ragflow
RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses...
GiovanniPasq/agentic-rag-for-dummies
A modular Agentic RAG built with LangGraph — learn Retrieval-Augmented Generation Agents in minutes.
truefoundry/cognita
RAG (Retrieval Augmented Generation) Framework for building modular, open source applications...
vectara/py-vectara-agentic
A python library for creating AI assistants with Vectara, using Agentic RAG