zjunlp/AutoAct

[ACL 2024] AutoAct: Automatic Agent Learning from Scratch for QA via Self-Planning

37
/ 100
Emerging

This project helps create a specialized AI assistant that can answer complex questions by automatically learning to use specific tools, without needing extensive human-labeled examples. It takes a small set of example questions and a library of available tools as input, and outputs a refined AI agent capable of breaking down questions, selecting the right tools, and reflecting on its answers. This is ideal for organizations that need a cost-effective way to deploy tailored AI question-answering systems.

235 stars. No commits in the last 6 months.

Use this if you need to build a specialized AI question-answering agent that can effectively use external tools, but you want to minimize the manual effort and cost associated with training data.

Not ideal if you need a general-purpose conversational AI without tool integration, or if you already have extensive human-annotated datasets for your specific task.

AI-powered-question-answering intelligent-agents knowledge-management automated-tool-use
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 11 / 25

How are scores calculated?

Stars

235

Forks

13

Language

Python

License

Apache-2.0

Last pushed

Jan 13, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/agents/zjunlp/AutoAct"

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