Add AYA Pipeline results for BFCL leaderboard - #1342
Open
Trizz-ai wants to merge 1 commit into
Open
Conversation
System: AYA multi-agent pattern execution pipeline Model: gpt-4o-mini (via AYA orchestration layer) Categories: 22/23 (4751 predictions) Overall accuracy: 44.3% (2191/4951) AYA is an AI agent framework that routes tasks through a pattern engine with overlay-driven configuration, multi-provider LLM fallback, and 12 specialized agents. Method: Each BFCL task is routed through AYA's pattern engine which handles prompt construction, function schema injection, and response extraction. No fine-tuning. Provenance: - Git SHA: 6d58042c5342 - Run date: 2026-06-02 - Framework: github.com/Trizz-ai/AYA
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
AYA Pipeline — BFCL Leaderboard Submission
System Description
AYA is a multi-agent AI framework that routes tasks through a pattern execution engine with overlay-driven configuration, multi-provider LLM fallback, and 12 specialized agents.
Model
Results
Provenance
File Format
Each file follows the BFCL standard format: one JSONL per category with model predictions.