Evolving Code with A Large Language Model
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913196161368064 |
|---|---|
| author | Hemberg, Erik Moskal, Stephen O'Reilly, Una-May |
| author_facet | Hemberg, Erik Moskal, Stephen O'Reilly, Una-May |
| contents | Algorithms that use Large Language Models (LLMs) to evolve code arrived on the Genetic Programming (GP) scene very recently. We present LLM GP, a formalized LLM-based evolutionary algorithm designed to evolve code. Like GP, it uses evolutionary operators, but its designs and implementations of those operators radically differ from GP's because they enlist an LLM, using prompting and the LLM's pre-trained pattern matching and sequence completion capability. We also present a demonstration-level variant of LLM GP and share its code. By addressing algorithms that range from the formal to hands-on, we cover design and LLM-usage considerations as well as the scientific challenges that arise when using an LLM for genetic programming. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_07102 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Evolving Code with A Large Language Model Hemberg, Erik Moskal, Stephen O'Reilly, Una-May Neural and Evolutionary Computing Artificial Intelligence I.2.8 Algorithms that use Large Language Models (LLMs) to evolve code arrived on the Genetic Programming (GP) scene very recently. We present LLM GP, a formalized LLM-based evolutionary algorithm designed to evolve code. Like GP, it uses evolutionary operators, but its designs and implementations of those operators radically differ from GP's because they enlist an LLM, using prompting and the LLM's pre-trained pattern matching and sequence completion capability. We also present a demonstration-level variant of LLM GP and share its code. By addressing algorithms that range from the formal to hands-on, we cover design and LLM-usage considerations as well as the scientific challenges that arise when using an LLM for genetic programming. |
| title | Evolving Code with A Large Language Model |
| topic | Neural and Evolutionary Computing Artificial Intelligence I.2.8 |
| url | https://arxiv.org/abs/2401.07102 |