Awesome
Original Reflexion Implementation
This is outdated: the main repository is located at https://github.com/noahshinn/reflexion
Code for the approach first proposed in Reflexion: an autonomous agent with dynamic memory and self-reflection
Note
Reflexion is not a replacement for ReAct or any other decision-guiding approach! It is a simple retry technique that can be used enhance other approaches.
Check out the original blog post here.
Check out an interesting type-inference implementation OpenTau that uses a variation of Reflexion to play a 2-player game with type-checker.
If you have any questions, please contact noahrshinn@gmail.com
Cite
@article{shinn2023reflexion,
title={Reflexion: an autonomous agent with dynamic memory and self-reflection},
author={Shinn, Noah and Labash, Beck and Gopinath, Ashwin},
journal={arXiv preprint arXiv:2303.11366},
year={2023}
}