README.md

March 6, 2026 · View on GitHub

LLM4AD: Large Language Model for Algorithm Design

Website | Documentation | Examples | GUI

📖 Introduction

LLM4AD is an open-source Python-based Platform leveraging Large Language Models (LLMs) for Automatic Algorithm Design (AD). Please refer to the paper [LLM4AD] for detailed information, including the overview, methodology, and benchmark results.

LLM4AD is accomplished with Documents and Examples materials to support users and developers to easily test, build and deploy their own LLM4AD applications and conduct research.

LLM4AD was originally developed for optimisation tasks. The framework is versatile enough to be used in other areas, including machine learning, science discovery, game theory and engineering design.

For more information, see the contact list

🔥 News

2026.02 🎉🎉 New Champion! Our LLM4AD system won the CVRPLib BKS competition and established 51 new Best Known Solutions on large-scale CVRP benchmarks.
2026.01 🎉🎉 Our Survey Paper "A Systematic Survey on Large Language Models for Algorithm Design" has been accepted by ACM Computing Surveys ! A Rep for the Survey can be found here
2025.6 🎉🎉 We're excited to share that EoH recently set a New World Record in Circle Packing Problem, achieving a score of 2.63594 for 26 circles ! Results here
2025.6 🎉🎉 LLM4AD at CEC 2025 Tutorial !
2025.3 🎉🎉 LLM4AD at EMO 2025 Tutorial !
2024.12 🎉🎉 LLM4AD paper Released “LLM4AD: A Platform for Algorithm Design with Large Language Model" !
2024.11 🎉🎉 LLM4AD v1.0 Released !
2024.10 🎉🎉 Survey Paper “A Systematic Survey on Large Language Models for Algorithm Design” is online !

💡 Features of our package

Feature	Support / To be supported
Unified Interfaces for methods, tasks, LLMs	🔥Support
Evaluation acceleration: multiprocessing evaluation	🔥Support
Secure Evaluation: main process protection, timeout interruption	🔥Support
Logs: local logs, Wandb and Tensorboard support	🔥Support
GUI: methods selection, tasks selection, convergence, best algorithm, ...	🔥Support
Resume run	🔥Support
Support other programming languages	🚀Coming soon
More search methods	🚀Coming soon
More task examples	🚀Coming soon

🎁 Requirements & Installation

Important

The Python version MUST be larger or equal to Python 3.9, and less than Python 3.13.

Important

If you are testing machine learning tasks or using GUI, please install gym via pip install gym. Please note that the gym version may be conflict with your own Python environment, please refer to gym's docs to obtain appropriate version.

Please refer to requirements.txt
Please install numba (if you want to use Numba accelerate)
Please install tensorboard (if you want to use a Tensorboard logger)
Please install wandb (if you want to use wandb logger)
Please install gym (if you want to try GUI, and Machine Learning tasks)
Please install pandas (if you want to try Science Discovery tasks)
Please install all required packages in requirements.txt (if you want to use GUI)

Install LLM4AD locally

We suggest to install and run LLM4AD in conda env with python>=3.9, <3.13

$ cd LLM4AD
$ pip install .

Install LLM4AD using PiPy

We suggest to install and run LLM4AD in conda env with python>=3.9, <3.13

$ pip install llm4ad

💻 Example Usage

Quick Start:

Note

Configure your LLM api before running the script. For example:

Set host: 'api.deepseek.com'
Set key: 'your api key'
Set model: 'deepseek-chat'

from llm4ad.task.optimization.online_bin_packing import OBPEvaluation
from llm4ad.tools.llm.llm_api_https import HttpsApi
from llm4ad.method.eoh import EoH, EoHProfiler

if __name__ == '__main__':
    llm = HttpsApi(
        host='xxx',   # your host endpoint, e.g., api.openai.com, api.deepseek.com
        key='sk-xxx', # your key, e.g., sk-xxxxxxxxxx
        model='xxx',  # your llm, e.g., gpt-3.5-turbo, deepseek-chat
        timeout=20
    )
    task = OBPEvaluation()
    method = EoH(
        llm=llm,
        profiler=EoHProfiler(log_dir='logs/eoh', log_style='simple'),
        evaluation=task,
        max_sample_nums=20,
        max_generations=10,
        pop_size=4,
        num_samplers=1,
        num_evaluators=1,
        debug_mode=False
    )
    method.run()

More Examples:

Check Documents for more tasks and examples

GUI usage:

Important

Install all required packages in requirements.txt for GUI usage.

$ cd GUI
$ python run_gui.py

Check GUI Introduction for more information

📦 LLM4AD Search Methods

Methods	Paper title
EoH	Evolution of Heuristics: Towards Efficient Automatic Algorithm Design Using Large Language Model (ICML 2024) Algorithm Evolution using Large Language Model (Arxiv 2023, AEL, the early version of EoH)
MEoH	Multi-objective Evolution of Heuristic Using Large Language Model (AAAI 25)
FunSearch	Mathematical Discoveries from Program Search with Large Language Models (Nature 2024)
(1+1)-EPS (HillClimbing)	Understanding the Importance of Evolutionary Search in Automated Heuristic Design with Large Language Models (PPSN 2024)
ReEvo	Reevo: Large language models as hyper-heuristics with reflective evolution (NeurIPS 2024)
MCTS-AHD	Monte carlo tree search for comprehensive exploration in llm-based automatic heuristic design (ICML 2025)
LHNS	LLM-Driven Neighborhood Search for Efficient Heuristic Design (CEC 2025)
PartEvo	Partition to Evolve: Niching-enhanced Evolution with LLMs for Automated Algorithm Discovery (NeurIPS 2025)
LLaMEA	LLaMEA: A Large Language Model Evolutionary Algorithm for Automatically Generating Metaheuristics(IEEE TEVC 2025)
EoH-S	EoH-S: Evolution of Heuristic Set using LLMs for Automated Heuristic Design (AAAI 2026)
MLES	Multimodal LLM-assisted Evolutionary Search for Programmatic Control Policies (ICLR 2026)
Others	Coming soon

⚙️ LLM4AD Algorithm Design Tasks

Area	Algorithm Task	Paper
Optimization	[Online Bin Packing, Constructive heuristic]	paper
	Traveling Salesman Problem (TSP), Construct heuristic	paper
	Traveling Salesman Problem (TSP), Guided local search	paper
	1-dimensional Bin Packing (BP1D), Construct heuristic	paper
	2-dimensional Bin Packing (BP2D), Construct heuristic	paper
	Capacitated Facility Location Problem (CFLP), Construct heuristic	paper
	Knapsack Problem (KP), Construct heuristic	paper
	Quadratic Assignment Problem (QAP), Construct heuristic	paper
	Set Cover Problem (SCP), Construct heuristic	paper
	Flow Shop Scheduling Problem (FSSP), Construct heuristic	paper
	Flow Shop Scheduling Problem (FSSP), Guided local search	paper
	Bayesian Optimization, Cost-aware Acquisition Function Design	paper
	Co-Bench: Benchmarking Language Model Agents in Algorithm Search for Combinatorial Optimization	paper
	Pymoo MOEA/D	paper
Machine Learning	Adversarial Attack, Attack strategy	paper
	Acrobot, Heuristic (Agent)
	Cart Pole, Heuristic (Agent)
	Mountain Car, Heuristic (Agent)
Science Discovery	Computational fluid dynamics, Turbulence model design	paper
	Bacteria Growth, Function
	Oscillator, Equation
	Stress & Strain, Equation
Math	Admissible Sets	paper
coming soon ...

🤖 LLM Interfaces

There are three approaches on LLM interface implementation, check Tutorial on LLM interface implementation for more information.

Remote LLM API (e.g., GPT4o, GPT3.5, Gemini Pro, Deepseek ...) (<Recommended !!!>)
Local HuggingFace LLM Deployment (e.g., Llamacode, Llama, Gemma, Deepseek, ...)
Your Implementation If you want to use your own GPT API or local LLMs deployment, please create and add your interface in LLM

🏫 Tutorial: How to Use LLM4AD to Solve Your Algorithm Design Task

A Step-by-step Tutorial on using LLM4AD to solve your algorithm design task is provided here

:question:QAs

Find responses to some common questions in our Discussion Area

常见问题答疑

🪪 Licence

This project is licensed under the BSD-2-Clause - see the LICENSE file for details. Parts of this project use code licensed under the Apache License 2.0.

✨ Reference

If you find LLM4AD helpful please cite:

@article{liu2024llm4ad,
    title = {LLM4AD: A Platform for Algorithm Design with Large Language Model},
    author = {Fei Liu and Rui Zhang and Zhuoliang Xie and Rui Sun and Kai Li and Xi Lin and Zhenkun Wang and Zhichao Lu and Qingfu Zhang},
    year = {2024},
    eprint = {2412.17287},
    archivePrefix = {arXiv},
    primaryClass = {cs.AI},
    url = {https://arxiv.org/abs/2412.17287},
}

📒 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 (see our 📖 contribution guide) including developing code and ideas to improve our platform.
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.