人类谈判的自动调解器：通过结构化LLM流水线进行预调解
Automated Mediator for Human Negotiation: Pre-Mediation via a Structured LLM Pipeline
AI总结：
提出一种结构化LLM流水线作为自动调解器，在整合性谈判中支持预调解，通过分解准备任务为专用模块，在短期自我报告结果上与人类调解员相当，并在偏好推理任务上误差降低36%。
摘要：
预调解是直接人类谈判前的准备阶段，在达成互利协议中起着关键作用，但由于成本、时间和缺乏训练有素的调解员而常被省略。我们引入了一种用于人类谈判的自动调解器，实现为结构化LLM模块流水线，在整合性谈判环境中支持预调解。该流水线将准备分解为对话、偏好预测、响应级批评和结构化总结的专用模块，分离推理、生成和评估，以解决单一提示方法的局限性。我们按照常见的LLM系统术语将每个模块称为“智能体”，但组件并非自主且不进行点对点交互；输出按固定顺序向前传递。我们在两个受控人类受试者实验中评估该系统，在多议题谈判场景中将基于AI的预调解与专业人类调解员进行比较。在短期自我报告测量中，自动调解器在准备结果上与人类调解员大致相当，包括对调解员的信任和达成互利协议的信心，同时在我们场景和提示下，偏好推理任务的误差显著降低（RMSE降低36%）。第二项研究表明，有针对性的提示优化将过度肯定模式从36.6%降至16.8%，与人类调解员基线匹配。我们的发现表明，结构化LLM流水线可以在短期自我报告准备结果上提供与人类调解员大致相当的可扩展、低投入的预调解支持。该流水线的单方设计反映了当前人类调解员进行预调解的方式，并支持在争议各方之间并行部署，从而实现可扩展性。
英文摘要：
Pre-mediation, the preparatory phase preceding direct human negotiation, plays a critical role in achieving mutually beneficial agreements, yet is often omitted due to cost, time, and limited access to trained mediators. We introduce an automated mediator for human negotiation, implemented as a structured pipeline of LLM modules, that supports pre-mediation in integrative negotiation settings. The pipeline decomposes preparation into specialized modules for dialogue, preference prediction, response-level critique, and structured summarization, separating inference, generation, and evaluation to address limitations of monolithic single-prompt approaches. We use the term "agent" for each module following common LLM-systems terminology, but the components are not autonomous and do not interact peer-to-peer; outputs are passed forward in a fixed sequence. We evaluate the system in two controlled human-subject experiments comparing AI-based pre-mediation with professional human mediators in a multi-issue negotiation scenario. On short-term self-reported measures, the automated mediator achieves preparation outcomes broadly comparable to human mediators, including trust in the mediator and confidence in reaching mutually beneficial agreements, while achieving substantially lower error on the preference-inference task under our scenario and prompts (36% lower RMSE). A second study shows that targeted prompt refinements reduce excessive affirmation patterns from 36.6% to 16.8%, matching human mediator baselines. Our findings suggest that structured LLM pipelines can provide scalable, low-effort pre-mediation support broadly comparable to human mediators on short-term self-reported preparation outcomes. The pipeline's single-party design mirrors how human mediators run pre-mediation today and enables parallel deployment across all parties to a dispute, supporting scalability.
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。
