AgenticPay: 一种基于多智能体LLM的买方卖方交易谈判系统
AgenticPay: A Multi-Agent LLM Negotiation System for Buyer-Seller Transactions
AI总结：
AgenticPay是一种基于多智能体LLM的买方卖方交易谈判系统，通过自然语言驱动的多轮谈判解决市场交易问题，评估智能体在经济互动中的表现。
摘要：
基于大型语言模型（LLM）的智能体日益被期望能够自主进行协商、协调和交易，但现有的基准测试缺乏对多个智能体之间语言媒介经济互动进行评估的系统性设置。我们介绍了AgenticPay，一种用于由自然语言驱动的多智能体买方卖方谈判的基准和模拟框架。AgenticPay模拟了买家和卖家具有私人约束和产品依赖性估值的市场，并必须通过多轮语言谈判达成协议，而不是仅通过数字竞价。该框架支持超过110种任务的多样化套件，从双边谈判到多对多市场，具有结构化的动作提取和衡量可行性、效率和福利的指标。对最先进的专有和开源LLM进行基准测试，揭示了谈判性能中的显著差距，并突显了长周期战略推理的挑战，确立了AgenticPay作为研究智能体商业和基于语言的市场互动的基础。代码和数据集可在链接处获得：https://github.com/SafeRL-Lab/AgenticPay。
英文摘要：
Large language model (LLM)-based agents are increasingly expected to negotiate, coordinate, and transact autonomously, yet existing benchmarks lack principled settings for evaluating language-mediated economic interaction among multiple agents. We introduce AgenticPay, a benchmark and simulation framework for multi-agent buyer-seller negotiation driven by natural language. AgenticPay models markets in which buyers and sellers possess private constraints and product-dependent valuations, and must reach agreements through multi-round linguistic negotiation rather than numeric bidding alone. The framework supports a diverse suite of over 110 tasks ranging from bilateral bargaining to many-to-many markets, with structured action extraction and metrics for feasibility, efficiency, and welfare. Benchmarking state-of-the-art proprietary and open-weight LLMs reveals substantial gaps in negotiation performance and highlights challenges in long-horizon strategic reasoning, establishing AgenticPay as a foundation for studying agentic commerce and language-based market interaction. Code and dataset are available at the link: https://github.com/SafeRL-Lab/AgenticPay.
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。
