EUVIMEDEUVIMED entdecken
Crossref

A²Flow: 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

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (35) · 29930-29938

DOI: 10.1609/aaai.v40i35.40240 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Mingming Zhao und 7 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

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 A²Flow, a fully automated framework for agentic workflow generation based on self-adaptive abstraction operators. A²Flow 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 A²Flow achieves a 2.4% and 19.3% average performance improvement and reduces resource usage by 37% over state-of-the-art baselines.

Zitieren

APA

Zhao, M., Wei, X., Shao, Y., Zhou, K., Yang, L., Rao, S., Zhan, J., & Chen, Z. (2026). A²Flow: Automating Agentic Workflow Generation via Self-Adaptive Abstraction Operators. Proceedings of the AAAI Conference on Artificial Intelligence, 40(35), 29930-29938. https://doi.org/10.1609/aaai.v40i35.40240

Vancouver

Zhao M, Wei X, Shao Y, Zhou K, Yang L, Rao S, et al. A²Flow: Automating Agentic Workflow Generation via Self-Adaptive Abstraction Operators. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(35):29930-29938. doi:10.1609/aaai.v40i35.40240

BibTeX
@article{Zhao2026,
  author = {Zhao, Mingming and Wei, Xiaokang and Shao, Yuanqi and Zhou, Kaiwen and Yang, Lin and Rao, Siwei and Zhan, Junhui and Chen, Zhitang},
  title = {A²Flow: Automating Agentic Workflow Generation via Self-Adaptive Abstraction Operators},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {35},
  pages = {29930--29938},
  doi = {10.1609/aaai.v40i35.40240}
}
Kostenlos starten →