@inproceedings{liu-etal-2026-promediate,
    title = "{P}ro{M}ediate: A Simulation Testbed for Evaluating Proactive Mediation in Multi-Party Negotiation",
    author = "Liu, Ziyi  and
      Sarrafzadeh, Bahareh  and
      Zhou, Pei  and
      Yang, Longqi  and
      Zhao, Jieyu  and
      Sharma, Ashish",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.findings-acl.1479/",
    pages = "29570--29598",
    ISBN = "979-8-89176-395-1",
    abstract = "While LLMs increasingly assist individual users, there is a critical need for agents that can proactively manage complex, multi-party collaboration. However, the scarcity of systematic evaluation methods for these group dynamics limits the development of AI capable of effectively supporting teams Here, we present ProMediate, the first testbed for evaluating proactive AI mediator agents in complex, multi-topic, multi-party negotiations. ProMediate consists of two core components: (i) a simulation environment based on realistic negotiation cases with a plug-and-play proactive AI mediator, capable of flexibly deciding when and how to intervene; and (ii) a socio-cognitive evaluation framework with a new suite of metrics to measure consensus changes, intervention latency, mediator effectiveness, and intelligence. These components establish a systematic framework for assessing the capability of proactive AI agents in multi-party settings. Our results show that a socially intelligent mediator agent outperforms a generic baseline, via faster, better-targeted interventions. In the ProMediate-Hard setting, our social mediator increases consensus change by 3.6 percentage points compared to the generic baseline (10.65{\%} vs 7.01{\%}) while being 77{\%} faster in response (15.98s vs. 3.71s). In conclusion, ProMediate provides a rigorous, theory-grounded testbed to advance the development of proactive, socially intelligent agents."
}