@inproceedings{liu-etal-2026-adaptive,
    title = "Adaptive Prompt Structure Factorization: A Framework for Self-Discovering and Optimizing Compositional Prompt Programs",
    author = "Liu, Haoyue  and
      Wang, Zhichao  and
      Guo, Yongxin  and
      Shou, Haoran  and
      Tang, Xiaoying",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.acl-long.537/",
    pages = "11690--11714",
    ISBN = "979-8-89176-390-6",
    abstract = "Automated prompt optimization is crucial for eliciting reliable reasoning from large language models (LLMs), yet most API-only prompt optimizers iteratively edit monolithic prompts, coupling components and obscuring credit assignment, limiting controllability, and wasting tokens. We propose Adaptive Prompt Structure Factorization (aPSF), an API-only framework (prompt-in/text-out; no access to model internals) that uses an Architect model to discover task-specific prompt structures as semantic factors. aPSF then performs interventional, single-factor updates: interventional factor-level scoring estimates each factor{'}s marginal contribution via validation-performance changes, and error-guided factor selection routes updates to the current dominant failure source for more sample-efficient optimization. Across multiple advanced reasoning benchmarks, aPSF outperforms strong baselines, improving accuracy by up to +4.29 percentage points on average, and reduces optimization cost by 45{--}87{\%} tokens on MultiArith while reaching peak validation in 1 step."
}