@inproceedings{liu-etal-2026-analyzing,
    title = "Analyzing and Internalizing Complex Policy Documents for {LLM} Agents",
    author = "Liu, Jiateng  and
      Wang, Zhenhailong  and
      Huang, Xiaojiang  and
      Li, Yingjie  and
      Li, Xiang  and
      Guo, Chenlei  and
      Fan, Xing  and
      Sarikaya, Ruhi  and
      Ji, Heng",
    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.767/",
    pages = "16814--16851",
    ISBN = "979-8-89176-390-6",
    abstract = "Large language model agents rely on in-context policy documents encoding diverse business rules. As businesses scale, these documents grow, creating substantial computational overhead and motivating internalization methods that embed policy into model priors. Prior work focuses on generic prompts, but we find agentic policies span multiple complexity levels and demand heavier reasoning, posing greater challenges. We introduce an agentic benchmark generator with Controllable Complexity in agent policy across four levels, enabling systematic evaluation of agents under increasing complexity and providing a testbed for policy internalization. Our analysis shows that workflow-governing policy specifications are the hardest to reason over, and that SFT on gold trajectories with chain-of-thought is data-hungry and struggles at high complexity. We propose Category-Aware Policy Continued Pretraining, an automated pipeline that analyzes policies, extracts key specifications, categorizes them into factual, behavioral, and conditional types, and isolates those driving workflow complexity. This enables targeted ``therapy'' by synthesizing specialized training data for each type and improving internalization via an autoregressive pretraining loss. Extensive experiments show our synthetic data and objective consistently improve performance. Combined with SFT, our method outperforms the baseline across different settings, especially in data-sparse and high-complexity regimes, with gains up to 41{\%} and 22{\%} on Qwen-3-32B. Overall, we achieve 97.3{\%} prompt reduction on our benchmark, and on $\tau$-Bench we further improve performance while reducing prompt requirements with very limited SFT data."
}