Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

LLM4AD: A Platform for Algorithm Design with Large Language Model

About

We introduce LLM4AD, a unified Python platform for algorithm design (AD) with large language models (LLMs). LLM4AD is a generic framework with modularized blocks for search methods, algorithm design tasks, and LLM interface. The platform integrates numerous key methods and supports a wide range of algorithm design tasks across various domains including optimization, machine learning, and scientific discovery. We have also designed a unified evaluation sandbox to ensure a secure and robust assessment of algorithms. Additionally, we have compiled a comprehensive suite of support resources, including tutorials, examples, a user manual, online resources, and a dedicated graphical user interface (GUI) to enhance the usage of LLM4AD. We believe this platform will serve as a valuable tool for fostering future development in the merging research direction of LLM-assisted algorithm design.

Fei Liu, Rui Zhang, Zhuoliang Xie, Rui Sun, Kai Li, Qinglong Hu, Ping Guo, Xi Lin, Xialiang Tong, Mingxuan Yuan, Zhenkun Wang, Zhichao Lu, Qingfu Zhang• 2024

Related benchmarks

TaskDatasetResultRank
Online Bin PackingOnline BPP (test)
Gap (%)0.445
120
Traveling Salesperson ProblemTSP N=200 (Generalization (128 instances))
Optimality Gap14.403
35
Traveling Salesperson ProblemTSP N=1000 Generalization (128 instances)
Optimality Gap16.076
30
Traveling Salesperson ProblemTSP N=500 Generalization (128 instances)
Optimality Gap15.232
30
Traveling Salesperson ProblemTSP n=100 (train)
Objective Value8.786
26
Traveling Salesperson ProblemTSP-20 (train)
Objective Value4.197
17
Traveling Salesperson ProblemTSP-50 (train)
Objective Value6.399
17
Traveling Salesperson ProblemTSP Overall
Average Gap13.343
16
Capacitated Vehicle Routing ProblemCVRP (train)
CVRP Cost (20)4.826
4
Offline Bin Packing ProblemOffline BPP Generalization
Bins Used (N=500, C=300)102.4
4
Showing 10 of 14 rows

Other info

Follow for update