$A^2Flow:$ Automating Agentic Workflow Generation via Self-Adaptive Abstraction Operators
This addresses the scalability and generalization limitations in agentic workflow automation for AI and robotics applications, representing a novel method rather than an incremental improvement.
The paper tackles the problem of automating agentic workflow generation by proposing A^2Flow, a framework that uses self-adaptive abstraction operators to eliminate reliance on manually predefined operators, achieving a 2.4% to 19.3% performance improvement and reducing resource usage by 37% over state-of-the-art baselines.
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 $A^2Flow$, a fully automated framework for agentic workflow generation based on self-adaptive abstraction operators. $A^2Flow$ 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 reusable building blocks for workflow construction without manual predefinition. Furthermore, we enhance node-level workflow search with an operator memory mechanism, which retains historical outputs to enrich context and improve decision-making. Experiments on general and embodied benchmarks show that $A^2Flow$ achieves a 2.4\% and 19.3\% average performance improvement and reduces resource usage by 37\% over state-of-the-art baselines. Homepage:https://github.com/pandawei-ele/A2FLOW