Welcome to LLM4AD Docs!#
Large language model for algorithm design (LLM4AD) platform has established an efficient, large language model-based framework for algorithm design, aimed at assisting researchers and related users in this field to conduct experimental exploration and industrial applications more quickly and conveniently.
🔥News#
Nov 5th, 2024: LLM4AD 1.0.0 is released.
🚀Coming soon#
Other programming languages support.
🌟Features#
LLM4AD unifies interfaces for multiple methods.
Evaluation acceleration: multiprocessing evaluation, add numba wrapper for algorithms.
Secure evaluation: main process protection, timeout interruption.
Log and profiling: Wandb and Tensorboard support.
Resume runs are supported.
LLM4AD provides package for code modification and secure evaluation for future development.
LLM4AD provides GUI support.
📦Supported methods#
LLM4AD implements state-of-the-art large language model based algorithm design methods.
Note
💡: The implementation has some minor differences from the original method (demonstrated in their original paper), considering generality and multithreading acceleration.
Tip
We also provide LLM-free examples to help understanding/building the pipeline of these methods!
🚌Supported tasks#
LLM4AD provides various example tasks including machine learning, optimization, and science discovery.
Domain |
Tasks |
|---|---|
Machine learning |
Acrobot, Cart Pole, Mountain Car |
Optimization |
CVRP, OVRP, TSP, VRPTW |
Science discovery |
Bacteria Grow, Ordinary Differential Equation, Oscillator 1, Oscillator 2, Stress Strain |
📝About LLM4AD#
This platform is developed and maintained by LLM4AD developer group from the City University of Hong Kong (CityUHK) and the Southern University of Science and Technology (SUSTech). We develop LLM4AD platform for research purposes and hope to contribute to the research area by delivering tools for LLM-based algorithm design methods.
Contribution: We are more than welcome to contribute including developing code and ideas to improve our platform. We are appreciated if you could give us a 🌟 on GitHub.
Collaborations: If you like our platform, and you would like to use it for profit-making purposes? We are always searching for industrial collaborations because they help direct research to meet the industry’s needs.
Issue: If you find a bug or you have any kind of concern regarding the correctness, please report us an issue.
Profit Purpose: If you intend to use LLM4AD for any profit-making purposes, please contact us.