ProMediate：多方谈判中评估主动代理的社认知框架
ProMediate: A Socio-cognitive framework for evaluating proactive agents in multi-party negotiation
AI总结：
本文提出ProMediate框架，用于评估多方谈判中主动代理的社认知能力，通过模拟测试平台和新指标衡量共识变化、干预延迟等，结果显示社会智能代理在复杂谈判中表现更优。
摘要：
尽管大型语言模型（LLMs）越来越多地用于代理框架以帮助个体用户，但需要能够主动管理复杂多方协作的代理。系统评估方法仍然匮乏，限制了开发能有效支持多人的AI进展。谈判为这一挑战提供了严苛的测试环境，要求社认知智能以导航多方参与者和多个主题间的冲突利益并建立共识。本文提出ProMediate，首个评估主动AI调解代理在复杂、多主题、多方谈判中的框架。ProMediate包含两个核心组件：（i）基于现实谈判案例和理论驱动难度级别的模拟测试平台（ProMediate-Easy、ProMediate-Medium和ProMediate-Hard），并基于社认知调解理论的插拔式主动AI调解器，能够灵活决定何时和如何干预；（ii）社认知评估框架，包含新指标集以衡量共识变化、干预延迟、调解有效性及智能。这些组件共同建立了一个系统框架，用于评估多方环境中主动AI代理的社认知智能。结果表明，社会智能调解代理在复杂谈判中优于通用基线，通过更快、更精准的干预。在ProMediate-Hard设置中，社会调解器相比通用基线使共识变化增加3.6个百分点（10.65% vs 7.01%），响应速度加快77%（15.98s vs 3.71s）。总之，ProMediate提供了一个严谨、理论驱动的测试平台，以推进主动、社会智能代理的发展。
英文摘要：
While Large Language Models (LLMs) are increasingly used in agentic frameworks to assist individual users, there is a growing need for agents that can proactively manage complex, multi-party collaboration. Systematic evaluation methods for such proactive agents remain scarce, limiting progress in developing AI that can effectively support multiple people together. Negotiation offers a demanding testbed for this challenge, requiring socio-cognitive intelligence to navigate conflicting interests between multiple participants and multiple topics and build consensus. Here, we present ProMediate, the first framework for evaluating proactive AI mediator agents in complex, multi-topic, multi-party negotiations. ProMediate consists of two core components: (i) a simulation testbed based on realistic negotiation cases and theory-driven difficulty levels (ProMediate-Easy, ProMediate-Medium, and ProMediate-Hard), with a plug-and-play proactive AI mediator grounded in socio-cognitive mediation theories, 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. Together, these components establish a systematic framework for assessing the socio-cognitive intelligence 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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
