@inproceedings{liu-etal-2026-costbench,
    title = "{C}ost{B}ench: Evaluating Multi-Turn Cost-Optimal Planning and Adaptation in Dynamic Environments for {LLM} Tool-Use Agents",
    author = "Liu, Jiayu  and
      Qian, Cheng  and
      Su, Zhaochen  and
      Zong, Qing  and
      Huang, Shijue  and
      He, Bingxiang  and
      Fung, Yi R.",
    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.584/",
    pages = "12826--12858",
    ISBN = "979-8-89176-390-6",
    abstract = "Current evaluations of Large Language Model (LLM) agents primarily emphasize task completion, often overlooking resource efficiency and adaptability. This neglects a crucial capability: agents' ability to devise and adjust cost-optimal plans in response to changing environments. To bridge this gap, we introduce **CostBench**, a scalable, cost-centric benchmark designed to evaluate agents' economic reasoning and replanning abilities. Situated in the travel-planning domain, CostBench comprises tasks solvable via multiple sequences of atomic and composite tools with diverse, customizable costs. It also supports four types of dynamic blocking events, such as tool failures and cost changes, to simulate real-world unpredictability and necessitate agents to adapt in real time. Evaluating leading open-sourced and proprietary models on CostBench reveals a substantial gap in cost-aware planning: agents frequently fail to identify cost-optimal solutions in static settings, with even *GPT-5* achieving less than 75{\%} exact match rate on the hardest tasks, and performance further drops significantly under dynamic conditions. By diagnosing these weaknesses, CostBench lays the groundwork for developing future agents that are both economically rational and robust."
}