An empirical evaluation of 22 agentic frameworks on BBH, GSM8K, and ARC benchmarks shows stable performance in 12 frameworks but highlights orchestration failures and weaker mathematical reasoning.
https://arcprize.org/leaderboard
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Agentic Frameworks for Reasoning Tasks: An Empirical Study
An empirical evaluation of 22 agentic frameworks on BBH, GSM8K, and ARC benchmarks shows stable performance in 12 frameworks but highlights orchestration failures and weaker mathematical reasoning.