shizhl/Confucius
Official code for AAAI2023 paper`Confucius: Iterative Tool Learning from Introspection Feedback by Easy-to-Difficult Curriculum`
This project helps AI developers train large language models (LLMs) to use external tools more effectively, enabling them to solve real-world problems. It takes a base LLM and a dataset of tool-use examples (like calculations or data lookups), and produces an LLM that can skillfully plan and execute complex tasks by calling the right tools. The primary users are AI/ML engineers working on agentic LLM applications.
No commits in the last 6 months.
Use this if you are an AI/ML engineer looking to train open-source large language models to intelligently select and utilize external tools for practical, multi-step tasks.
Not ideal if you are looking for a pre-trained, ready-to-deploy agent or do not have the technical expertise to train large language models.
Stars
45
Forks
12
Language
Python
License
—
Category
Last pushed
Feb 09, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/shizhl/Confucius"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
langfengQ/verl-agent
verl-agent is an extension of veRL, designed for training LLM/VLM agents via RL. verl-agent is...
sotopia-lab/sotopia
Sotopia: an Open-ended Social Learning Environment (ICLR 2024 spotlight)
zhudotexe/redel
ReDel is a toolkit for researchers and developers to build, iterate on, and analyze recursive...
TIGER-AI-Lab/verl-tool
A version of verl to support diverse tool use
AMAP-ML/Tree-GRPO
[ICLR 2026] Tree Search for LLM Agent Reinforcement Learning