mangopy/Confucius-tool-learning

Official Repo for AAAI 2024 paper "Confucius: Iterative Tool Learning from Introspection Feedback by Easy-to-Difficult Curriculum"

36
/ 100
Emerging

This project helps AI developers enhance large language models (LLMs) to effectively use external tools, mimicking human problem-solving. It takes a base LLM and a dataset of tasks requiring tool use (like calculations or API calls) and outputs a more capable LLM that can identify and apply the right tools for complex, real-world problems. This is for AI researchers and machine learning engineers looking to build more robust and versatile AI agents.

159 stars. No commits in the last 6 months.

Use this if you are developing AI agents and need to train large language models to autonomously select and utilize various tools to solve complex tasks.

Not ideal if you are an end-user looking for a pre-built application, as this is a framework for training and research, not a ready-to-use tool.

AI-agent-development LLM-training tool-integration curriculum-learning machine-learning-research
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 10 / 25

How are scores calculated?

Stars

159

Forks

9

Language

Python

License

Apache-2.0

Last pushed

Mar 07, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/mangopy/Confucius-tool-learning"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.