https://github.com/noahshinn/reflexion-draft

Reflexion: an autonomous agent with dynamic memory and self-reflection
https://github.com/noahshinn/reflexion-draft

artificial-intelligence llm

Last synced: about 2 months ago
JSON representation

Reflexion: an autonomous agent with dynamic memory and self-reflection

• Host: GitHub
• URL: https://github.com/noahshinn/reflexion-draft
• Owner: noahshinn
• License: mit
• Created: 2023-03-20T15:04:37.000Z (over 1 year ago)
• Default Branch: main
• Last Pushed: 2023-11-26T01:06:38.000Z (10 months ago)
• Last Synced: 2024-07-09T02:55:56.934Z (3 months ago)
• Topics: artificial-intelligence, llm
• Language: Python
• Homepage:
• Size: 1.83 MB
• Stars: 377
• Watchers: 10
• Forks: 41
• Open Issues: 2
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# Original Reflexion Implementation

### This is outdated: the main repository is located at [https://github.com/noahshinn/reflexion](https://github.com/noahshinn/reflexion)

Code for the approach first proposed in [Reflexion: an autonomous agent with dynamic memory and self-reflection](https://arxiv.org/abs/2303.11366)

### Note

Reflexion is not a replacement for [ReAct](https://github.com/ysymyth/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](https://nanothoughts.substack.com/p/reflecting-on-reflexion) here.

Check out an interesting type-inference implementation [OpenTau](https://github.com/GammaTauAI/opentau) that uses a variation of Reflexion to play a 2-player game with type-checker.

If you have any questions, please contact [[email protected]]([email protected])

### Cite

```bibtex

@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}

}

```