Enhance Action Generalization by Fetching Relevant Tasks for Prompting #6
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
petrpan26
force-pushed
the
openai-api
branch
3 times, most recently
from
3a03b1f to
f1ce2b4
Compare
|
@dangne Pls review |
petrpan26
changed the title
petrpan26
force-pushed
the
openai-api
branch
2 times, most recently
from
454b13a to
6c86336
Compare
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.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.
Changes implemented:
This PR introduces an enhancement to DynaSaur by improving the generalization of generated actions.
Instead of relying solely on predefined actions and task, this update enables the system to dynamically fetch relevant tasks in training set as an example and incorporate them into the prompt. By adding relevant example tasks to the prompt, the agent is guided to avoid generating overly specific actions tailored only to the current task. This approach fosters more reusable and adaptable actions across diverse scenarios.