[PB] Add BasicAgent solver#89
Merged
thesofakillers merged 1 commit intomainfrom Nov 28, 2025
Merged
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
This PR creates a
PythonCodingSolverport of our plonked AISI Basic Agent in both it's original and iterative variants.To be clear, this ports the aisi basic logic agent logic into a proper solver as expected by nanoeval -- API calls happen on the host, and we dont do any plonking and there is no agent image.
The only part missing is the web browser tool. For this we have opted to just rely on the browser tool usually afforded by API's, e.g. the responses API's
web_search_previewtool. This unfort means you can't evaluate e.g.o1with web searching since it doesn't support that tool.You'll find the port under
paperbench/agents/basicagent/.This PR does not yet delete
paperbench/agents/aisi-basic-agent/since deleting many files will lead to clunky/sluggishFiles changedtab. This PR will soon be followed with a handful of other PR(s) removing stale code and cleaning up paperbenchWe have deleted
ExternalPythonCodingSolverwhich was the solver we used for plonking.Some other notes worth pointing out:
agents/andsolvers/folder. I have consolidated these into a singleagents/folder. We will consolidate these back into asolvers/folder in a future PR about this. I know this sounds silly but bear with meExpect a few follow up PRs next week.