Repository navigation
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
R* extracts answers with
\d+, so an explicitThe final answer is -1.25falls back to25at reduced confidence, and1.75becomes1at full confidence. This changes both rollout rewards and the answer-frequency vote, even when the model generated the correct value.Use the same signed numeric pattern for explicit answers and the last-number fallback. Preserve decimal and scientific notation while retaining the existing confidence levels and integer behavior.
Validation:
python -m pytest tests/test_rstar_numeric_answers.py tests/test_rstar_backpropagation.py tests/test_conversation_logging_approaches.py -qpassed 15 tests and 34 subtests. The new cases cover extraction, rollout reward, decimal answer voting, and the fullsolve()path with mocked model responses. Before the fix, the negative-answer reward, decimal vote, and final output regressions fail. New-test Ruff andgit diff --checkpassed.