xingyaoww/code-act

Official Repo for ICML 2024 paper "Executable Code Actions Elicit Better LLM Agents" by Xingyao Wang, Yangyi Chen, Lifan Yuan, Yizhe Zhang, Yunzhu Li, Hao Peng, Heng Ji.

45
/ 100
Emerging

This project offers a sophisticated AI assistant designed to solve complex problems by writing and executing its own Python code. You give it a task in plain language, and it generates code, runs it, and uses the results to dynamically adjust its approach. It's ideal for anyone who needs an intelligent agent to automate multi-step, logic-heavy tasks that involve data processing or interacting with systems via code.

1,622 stars. No commits in the last 6 months.

Use this if you need an AI that can not only understand your instructions but also actively code and execute steps to reach a solution, adapting based on the live results.

Not ideal if your tasks are purely textual, involve subjective judgment without clear executable steps, or don't benefit from code-based problem-solving.

AI agents automated problem-solving code execution intelligent automation complex task management
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 19 / 25

How are scores calculated?

Stars

1,622

Forks

130

Language

Python

License

MIT

Last pushed

May 23, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/xingyaoww/code-act"

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