AFlow uses Monte Carlo Tree Search to automatically generate and optimize code-represented agentic workflows for LLMs, delivering a 5.7% average gain over prior methods on six benchmarks while letting smaller models beat GPT-4o at low cost.
"" async def __call__(self, problem: str):
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
AFlow: Automating Agentic Workflow Generation
AFlow uses Monte Carlo Tree Search to automatically generate and optimize code-represented agentic workflows for LLMs, delivering a 5.7% average gain over prior methods on six benchmarks while letting smaller models beat GPT-4o at low cost.