Connecting Large Language Models with Evolutionary Algorithms Yields Powerful Prompt Optimizers

Qingyan Guo, Rui Wang, Junliang Guo, Bei Li, Kaitao Song +4 more
2/12/2026

No official code found. Best implementation: beeevita/EvoPrompt (234 stars, MIT, last commit 2025-09-22). 2 more below.

DOISemantic Scholar

Code Implementations(3)

beeevita/EvoPromptCommunity75%
MIT

Official implementation of the paper Connecting Large Language Models with Evolutionary Algorithms Yields Powerful Prompt Optimizers

23436Shell, PythonOct 11, 20231 years agoMIT
kyegomez/EAOTCommunity70%
MIT

The open source implementation of "Connecting Large Language Models with Evolutionary Algorithms Yields Powerful Prompt Optimizers"

195Python, MakefileSep 21, 20232 years agoMIT
artificial-intelligencegpt4llamallama2machine-learning+2 more
danielrosen29/EvoPrompt_Implementation_and_QingyanGuo_Etal_AnalysisCommunity65%

This repo analyzes Qingyan Guo Et. al's paper "CONNECTING LARGE LANGUAGE MODELS WITH EVOLUTIONARY ALGORITHMS YIELDS POWERFUL PROMPT OPTIMIZERS" and implements EvoPrompt(GA) two ways.

30PythonOct 24, 20232 years ago

Cite this paper

@article{guo2026connecting,
  title  = {Connecting Large Language Models with Evolutionary Algorithms Yields Powerful Prompt Optimizers},
  author = {Qingyan Guo and Rui Wang and Junliang Guo and Bei Li and Kaitao Song and Xu Tan and Guoqing Liu and Jiang Bian and Yujiu Yang},
  year   = {2026},
  doi    = {10.48550/arXiv.2309.08532},
  url    = {https://arxiv.org/pdf/2309.08532},
  journal = {ICLR 2024 2024}
}

Discussion