@inproceedings{lin-etal-2026-agentask,
    title = "{A}gent{A}sk: Multi-Agent Systems Need to Ask",
    author = "Lin, Bohan  and
      Yang, Kuo  and
      Tan, Zelin  and
      Lai, Yingchuan  and
      Zhang, Chen  and
      Zhang, Guibin  and
      Yu, Xinlei  and
      Yu, Miao  and
      Wang, Xu  and
      Zhang, Yudong  and
      Wang, Yang",
    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.1294/",
    pages = "28055--28077",
    ISBN = "979-8-89176-390-6",
    abstract = "Multi-agent systems (MAS) built on large language models promise improved problem-solving through collaboration, yet they often fail to consistently outperform strong single-agent baselines due to error propagation at inter-agent message handoffs. In this work, we conduct a systematic empirical analysis of such failures and introduce an edge-level error taxonomy that identifies four dominant error types: Data Gap, Signal Corruption, Referential Drift, and Capability Gap, as primary sources of failure in multi-agent interactions. Building on this taxonomy, we propose AgentAsk, a lightweight clarification module designed to intervene at the edge level in MAS to prevent cascading errors. The module operates by strategically applying minimal clarifications at critical points within the system, improving the accuracy and efficiency of the overall task. AgentAsk is trained to balance the trade-offs between clarification cost, latency, and accuracy, while it is also architecture-agnostic and can be easily integrated into existing systems. Evaluated across five benchmarks, AgentAsk consistently improves accuracy by up to 4.69{\%}, while keeping latency and extra costs below 10{\%} compared to baseline MAS, showcasing its high efficiency and minimal overhead. The code is available at https://anonymous.4open.science/r/AgentAsk-3432."
}