@inproceedings{jiang-etal-2026-risklab,
    title = "{R}isk{L}ab: A Controlled Toolkit for Probing Emergent Risks in {LLM}-Based Multi-Agent Systems",
    author = "Jiang, Yu  and
      Wang, Wenjie  and
      Huang, Yue  and
      Wang, Yanbo  and
      Zhou, Zhenhong  and
      Chen, Xiuying  and
      Liu, Yang  and
      Chen, Pin-Yu  and
      Wang, Wei  and
      Zhang, Xiangliang",
    editor = "Durrett, Greg  and
      Jian, Ping",
    booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 3: System Demonstrations)",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.acl-demo.17/",
    pages = "167--177",
    ISBN = "979-8-89176-392-0",
    abstract = "Large language model (LLM) agents increasingly operate in multi-agent settings where failures emerge from interaction dynamics rather than isolated model errors. We introduce RiskLab, an open-source toolkit for instantiating, probing, and measuring emergent risks in LLM-based multi-agent systems under controlled conditions. Each experiment is defined as a structured topology{--}environment{--}protocol{--}agent{--}task quintuple, enabling reproducible studies of how communication structure, coordination mechanisms, and incentives shape system-level risks. RiskLab provides flexible communication topologies, swappable interaction protocols, trajectory-grounded evaluation, and extensible registries for risk detectors and agent backends. We demonstrate the toolkit across representative risks, including collusion, resource overreach, semantic drift, and strategic misreporting, and support one-file reproducibility via configuration."
}