Add Reflexion Agent Implementation #27
Closed
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
PalmPalm7
changed the title
PalmPalm7
changed the title
PalmPalm7
changed the title
Member
|
@PalmPalm7 were you going to refactor this based on the comment in the llama-stack-client-python repo with similar code? |
Collaborator
Author
Yes, working on it! Recent work on mult-agent gave me some insights on better designs, will refractor and merge soon. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Add ReflexionAgent Implementation
I've added a new
ReflexionAgentthat inherits from llama-stack-apps's ReAct Agent to create Reflexion Agent.Pull Request: llamastack/llama-stack-client-python#166
What is Reflexion?
It's a cool technique where agents reflect on their reasoning to improve accuracy, and reflexion improves on tasks with effective evaluation heuristics.
The implementation is based on the Reflexion paper and works great with Llama 3.1 models.