$A^2Flow:$ Automating Agentic Workflow Generation via Self-Adaptive Abstraction Operators
Mingming Zhao, Xiaokang Wei, Yuanqi Shao, Kaiwen Zhou, Lin Yang, Siwei Rao, Junhui Zhan, Zhitang Chen

TL;DR
A2Flow introduces a fully automated, self-adaptive framework for generating agentic workflows using abstraction operators, significantly improving performance and resource efficiency over existing methods.
Contribution
It presents a novel three-stage operator extraction process and an operator memory mechanism, enabling scalable and generalizable workflow automation without manual operator design.
Findings
Achieves 2.4% and 19.3% performance improvements on benchmarks.
Reduces resource usage by 37% compared to baselines.
Demonstrates effectiveness on general and embodied benchmarks.
Abstract
Large language models (LLMs) have shown strong potential in automating the design of agentic workflows. However, existing methods still rely heavily on manually predefined operators, limiting generalization and scalability. To address this issue, we propose , a fully automated framework for agentic workflow generation based on self-adaptive abstraction operators. employs a three-stage operator extraction process: 1) Case-based Initial Operator Generation: leveraging expert demonstrations and LLM reasoning to generate case-specific operators; 2) Operator Clustering and Preliminary Abstraction: grouping similar operators across tasks to form preliminary abstractions; and 3) Deep Extraction for Abstract Execution Operators: applying long chain-of-thought prompting and multi-path reasoning to derive compact and generalizable execution operators. These operators serve as…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsScientific Computing and Data Management · Machine Learning in Materials Science · Explainable Artificial Intelligence (XAI)
