LLM4Opt
FreeApplying Large language models (LLMs) for diverse optimization tasks (Opt) is an emerging research area. This is a collection of references and papers of LLM4Opt.
FreeFree tier
About LLM4Opt
A curated collection of references and papers on applying large language models (LLMs) for algorithm design and optimization (LLM4AD). Includes a systematic survey paper published in ACM Computing Surveys (2025), and covers platforms such as LLM4AD (open-source Python-based platform with 100+ tasks and 10+ methods), BLADE (benchmarking LLM-driven automated design of iterative optimization heuristics), and EASE (framework for effortless algorithmic solution evolution). Also lists relevant courses, tutorials, workshops, and special issues.
Key Features
Curated list of papers sorted by publication time
Systematic survey paper on LLMs for algorithm design (ACM Computing Surveys 2025)
Open-source Python platform LLM4AD with 100+ tasks and 10+ methods
BLADE benchmark for LLM-driven iterative optimization heuristics
EASE framework for automated algorithmic solution evolution
List of courses, tutorials, workshops, and special issues
Pros & Cons
Pros
- Comprehensive, up-to-date collection of relevant papers
- Includes a systematic survey providing an overview of the field
- Covers multiple platforms, benchmarks, and evaluation resources
- Open-source and freely accessible to everyone
- Community-driven with opportunities for contribution
Cons
- Not a standalone tool; it is a research repository and curated list
- Requires background knowledge in LLMs and optimization
- May not cover every relevant paper or resource
Best For
Research on applying LLMs to optimization and algorithm designAutomated algorithm generation and heuristic search with LLMsBenchmarking and comparing LLM-based algorithm design methodsEducation and tutorials on LLMs for optimization
FAQ
What is LLM4Opt?
LLM4Opt (also known as LLM4AlgorithmDesign) is a curated collection of references, papers, and resources on applying large language models to algorithm design and optimization. It includes a systematic survey and links to platforms, benchmarks, courses, and workshops.
Is LLM4Opt free to use?
Yes, the repository is open-source and freely accessible on GitHub.
How can I contribute to the collection?
You can fork the repository, add new papers or resources, and submit a pull request. Alternatively, you can report issues or contact the maintainer Fei Liu.