This repository serves as a curated collection of research papers and resources focused on the application of Large Language Models (LLMs) to various optimization tasks. It targets researchers and practitioners in fields like machine learning, evolutionary computation, and operations research, providing a centralized hub for the rapidly evolving intersection of LLMs and optimization.

How It Works

The collection categorizes papers by their approach to integrating LLMs with optimization, including LLM as optimizer, code generation, prompt optimization, and LLM-based surrogate models. It also highlights related resources such as courses, tutorials, competitions, and special journal issues, offering a comprehensive overview of the research landscape.

Quick Start & Requirements

This is a curated list of research papers and does not involve direct code execution or installation. Users can browse the categorized links to relevant papers, code repositories, and events.

Highlighted Details

• Comprehensive categorization of LLM applications in optimization, from algorithm design to industry use cases.
• Includes links to over 100 research papers, many with associated code repositories.
• Features a broad range of related resources including workshops, tutorials, and special journal issues.
• Covers emerging sub-fields like LLM-guided reinforcement learning and LLM-based hyper-heuristics.

Maintenance & Community

The project welcomes suggestions and pull requests for updates. Contact information for the primary contributor is provided. The sharing principle is for research purposes, with an option for authors to request removal.

Licensing & Compatibility

The repository itself is a collection of links and does not have a specific license. Individual papers and code repositories linked within will have their own respective licenses.

Limitations & Caveats

The collection explicitly states it is "far from a comprehensive list" and relies on community contributions for updates. Some linked papers may be pre-prints or in review stages.