并行还是让步？智能体商务中的并发感知采购谈判
Parallelism or Concession? Concurrency-Aware Procurement Negotiation for Agentic Commerce
- Nanjing University（南京大学）
- University of Tsukuba（筑波大学）
- University of Tokyo（东京大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
本文研究智能体采购中的并发谈判问题，提出并发感知谈判优化器（CANO），证明并行可替代让步，并确定最优并发度与价格上限，优于启发式策略。
AI中文摘要：
智能体买家可以廉价地将一项采购任务分解为多个并行谈判，但并发并非免费：每个线程都会消耗资源，同时达成的协议会产生取消和承诺风险。我们研究了一个在单一硬截止日期谈判窗口内的单单位后订单采购问题，其中规划者联合选择面向卖家的谈判者数量和共同的采购价格上限。该模型结合了产品特定的接受曲线与履约损失、每线程成本和超额承诺成本。我们建立了三个结构性结果。首先，在保持每线程接受目标固定的情况下，额外谈判者的边际价值呈几何衰减，从而产生条件并发阈值。其次，在凸分位数曲线下，并行替代让步：更多的并发谈判者意味着更低的每线程接受目标和价格上限。第三，当价格更加分散时，智能体买家通过更努力地寻找便宜货而受益，但若试图通过提供更高价格来保证采购，则会受损。我们将这些结果应用于并发感知谈判优化器（CANO），这是一个确定性优化器，为智能体采购系统联合确定最优谈判并发度和采购价格上限。在不同的分析市场配置以及广泛的蒙特卡洛、有限数据、非高斯和相关卖家压力测试中，CANO始终优于常见的启发式策略，同时验证了预测的结构性质。
英文摘要：
Agentic buyers can cheaply fork a procurement task into many parallel negotiations, but concurrency is not free: every thread consumes resources, and simultaneous agreements create cancellation and commitment risk. We study a one-unit post-order sourcing problem with a single hard-deadline negotiation window, in which a planner jointly chooses the number of seller-facing negotiators and a common procurement price cap. The model combines a product-specific acceptance curve with fulfillment loss, per-thread cost, and excess-commitment cost. We establish three structural results. First, holding the per-thread acceptance target fixed, the marginal value of another negotiator decays geometrically, yielding a conditional concurrency threshold. Second, under a convex quantile curve, parallelism substitutes for concession: more concurrent negotiators imply a weakly lower per-thread acceptance target and price cap. Third, when prices are more dispersed, Agentic buyers benefit by searching harder for bargains, but suffer when they instead try to guarantee procurement by offering higher prices. We operationalize these results in the Concurrency-Aware Negotiation Optimizer (CANO), a deterministic optimizer that jointly determines the optimal negotiation concurrency and procurement price cap for an agentic procurement system. Across different analytic market configurations and extensive Monte Carlo, finite-data, non-Gaussian, and correlated-seller stress tests, CANO consistently outperforms common heuristic policies while validating the predicted structural properties.
