zjunlp/TRICE
[NAACL 2024] Making Language Models Better Tool Learners with Execution Feedback
This project helps machine learning researchers and practitioners enhance how Large Language Models (LLMs) utilize external tools. It provides a two-stage training framework that takes existing LLM models and instruction-tuning datasets as input. The output is a more capable LLM that can selectively and effectively use tools based on execution feedback.
No commits in the last 6 months.
Use this if you are a researcher or ML engineer working to improve the reliability and accuracy of LLMs when they interact with and use external software tools or APIs.
Not ideal if you are looking for an off-the-shelf, plug-and-play solution for end-users to apply LLMs directly in business applications without further development.
Stars
43
Forks
3
Language
Python
License
MIT
Category
Last pushed
Mar 14, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/zjunlp/TRICE"
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