AgenticPay：面向买卖交易的多智能体大语言模型协商系统

摘要

基於大型語言模型（LLM）的智能體正被日益期待能自主進行協商、協作與交易，然而現有基準測試缺乏用於評估多智能體間語言媒介經濟互動的系統化設定。我們推出AgenticPay——一個專為自然語言驅動的多智能體買賣雙方協商而設計的基準測試與模擬框架。該框架模擬買賣雙方擁有私有約束條件和產品依賴性估值的市場環境，要求智能體必須通過多輪語言協商（而非僅靠數值出價）達成協議。該框架支持超過110種多樣化任務，從雙邊議價到多對多市場交易，並具備結構化行動提取功能及可行性、效率與福利等多維度指標。通過對標頂級專有模型與開源權重LLM的測試，我們發現現有模型在協商性能上存在明顯差距，並凸顯了長時程戰略推理的挑戰，從而確立AgenticPay作為研究智能商務與語言驅動市場互動的基礎平台。代碼與數據集可通過以下鏈接獲取：https://github.com/SafeRL-Lab/AgenticPay。

English

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.

AgenticPay：面向买卖交易的多智能体大语言模型协商系统

AgenticPay: A Multi-Agent LLM Negotiation System for Buyer-Seller Transactions

摘要

Support