@inproceedings{yang-etal-2026-attribution,
    title = "Attribution-Based Analysis and Optimization of Modular Agentic Workflows",
    author = "Yang, Yingxuan  and
      Huang, Bo  and
      Qi, Siyuan  and
      Feng, Chao  and
      Hu, Haoyi  and
      Zhu, Yuxuan  and
      Hu, Jinbo  and
      Zhao, Haoran  and
      He, Ziyi  and
      Liu, Xiao  and
      Wang, ZongYu  and
      Wen, Muning  and
      Qiu, Lin  and
      Cao, Xuezhi  and
      Cai, Xunliang  and
      Yu, Yong  and
      Zhang, Weinan",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.findings-acl.359/",
    pages = "7247--7264",
    ISBN = "979-8-89176-395-1",
    abstract = "Agentic workflows solve complex tasks by orchestrating modular components (e.g., planning, reasoning, action, reflection) built on top of LLM backbones. A practical but underexplored question is model allocation: given a fixed workflow decomposition and a pool of candidate LLMs, which components should be upgraded (and with which models) to upgrade task performance, and how can we attribute gains to individual upgrades and their interactions?We present ShapleyFlow, a cooperative game theoretic framework that models component upgrades as players and evaluates component coalitions to compute Shapley values. This yields interaction-aware attribution and supports Shapley-guided configuration recommendation for model allocation under a fixed workflow structure.We further introduce CapaBench, a benchmark of 1,500+ tasks across seven domains (shopping, navigation, ticketing, mathematics, operating systems, robotic coordination, and automated theorem proving).Across 9 representative LLMs and all $2^4$ upgrade coalitions in a 4-component workflow, ShapleyFlow provides (i) principled, interaction-aware attribution for modular workflows and (ii) actionable model-allocation recommendations that improve over strong single-model baselines."
}