EUVIMEDEUVIMED entdecken
Open Access · CC BY-ND 4.0

AgencyTree: Automated Multimedia Workflow Generation with Robust Planning via an Abstract Capability Tree

Wei Liu, Bowen Luo, Xiaohong Chen, Dongming Jin, Zhi Jin, Chengfei Yuan

ACM Transactions on Software Engineering and Methodology · 30.11.2026 · 35 (11) · 1-32

DOI: 10.1145/3812545 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACM Transactions on Software Engineering and Methodology, online erschienen am 03.11.2026. Verfasst von Wei Liu und 5 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 50 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-ND 4.0). Gefördert von: National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Despite the rapid progress in Generative AI, building applications that fulfill complex demands still requires the manual orchestration of multiple AI models into workflows, which is time-consuming and error-prone. Existing large language model (LLM)-based automation methods suffer from planning brittleness: they often produce infeasible plans due to an unstructured understanding of model capabilities, and their tightly coupled architectures are vulnerable to rapid changes in the underlying model ecosystem. To address this, we present AgencyTree , a novel multi-agent framework that introduces a formal Abstract Capability Tree (ACT) as a shared ontological knowledge base. This tree hierarchically abstracts concrete AI models into canonical functional nodes, decoupling high-level task planning from low-level model execution. Built upon this abstraction, five specialized agents—Knowledge Engineer, System Analyst, System Architect, Project Engineer, and Intent Consistency Verifier—collaborate to automate the workflow lifecycle. Evaluated on a comprehensive benchmark, AgencyTree achieves significantly higher task success and output quality than state-of-the-art baselines. Crucially, the framework exhibits exceptional robustness to model registry changes, with over 90% of abstract workflows being fully reusable without modification, thereby reducing adaptation overhead by orders of magnitude compared to re-planning from scratch. This work establishes a new paradigm for building reliable and dynamically adaptive AI assembly systems.

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Liu, W., Luo, B., Chen, X., Jin, D., Jin, Z., & Yuan, C. (2026). AgencyTree: Automated Multimedia Workflow Generation with Robust Planning via an Abstract Capability Tree. ACM Transactions on Software Engineering and Methodology, 35(11), 1-32. https://doi.org/10.1145/3812545

Vancouver

Liu W, Luo B, Chen X, Jin D, Jin Z, Yuan C. AgencyTree: Automated Multimedia Workflow Generation with Robust Planning via an Abstract Capability Tree. ACM Transactions on Software Engineering and Methodology. 2026;35(11):1-32. doi:10.1145/3812545

BibTeX
@article{Liu2026,
  author = {Liu, Wei and Luo, Bowen and Chen, Xiaohong and Jin, Dongming and Jin, Zhi and Yuan, Chengfei},
  title = {AgencyTree: Automated Multimedia Workflow Generation with Robust Planning via an Abstract Capability Tree},
  journal = {ACM Transactions on Software Engineering and Methodology},
  year = {2026},
  volume = {35},
  number = {11},
  pages = {1--32},
  doi = {10.1145/3812545}
}
Kostenlos starten →