Open neubig opened 3 months ago
Thanks for creating the issue! Although I don’t have much spare bandwidth recently, I am definitely interested in bringing EvalRefineResetStrategy and the retry functionality into OpenDevin. I will keep an eye on this PR and contribute once I have the time.
This issue is stale because it has been open for 30 days with no activity. Remove stale label or comment or this will be closed in 7 days.
This issue is stale because it has been open for 30 days with no activity. Remove stale label or comment or this will be closed in 7 days.
What problem or use case are you trying to solve?
Sometimes models fail to do their job correctly, and we would benefit from starting all over from the beginning. There are a few examples of this in the agent literature:
Describe the UX of the solution you'd like
Ideally, this would be something that could be implemented in a general way, so that we could implement different strategies with a shared interface. For instance:
Then, when using OpenDevin, we could choose an option that says "retry N times when you get stuck", and select the strategy that is used to do so.
Do you have thoughts on the technical implementation?
The actual reset strategies would vary based on the task. For instance:
initialize
: save the current git commit of the repositorycommit_id
verify
: tests+linting passreset
:git checkout commit_id
message_on_failure
: no-opinitialize
: save the current web pageinitial_page
verify
: the reward model is positivereset
:goto(initial_page)
message_on_failure
: reflexion promptThis could either be integrated into OpenDevin, allowing for retries in the main app as well
Additional context: