Strategic Bargaining in Multi-Buyer Markets: Reinforcement Learning from Verifiable Rewards for LLM Negotiations

📄 arXiv: 2607.05863v1 📥 PDF

作者: Shuze Daniel Liu, Claire Chen, Jiabao Sean Xiao, Xin Chen, David Simchi-Levi

分类: cs.LG, cs.GT

发布日期: 2026-07-07


💡 一句话要点

提出基于可验证奖励的强化学习方法以优化多买家市场谈判

🎯 匹配领域: 支柱二:RL算法与架构 (RL & Architecture) 支柱九:具身大模型 (Embodied Foundation Models)

关键词: 强化学习 经济决策 多买家市场 谈判策略 可验证奖励 模型训练 市场探索 深度学习

📋 核心要点

  1. 现有大型语言模型在多买家市场谈判中表现不佳,未能有效探索买家池,常常只关注当前最高出价。
  2. 本文提出了一种基于可验证奖励的强化学习方法,通过将奖励与经济结果挂钩,促进卖家在市场探索与利润提取之间的平衡。
  3. 实验结果显示,训练后的卖家在谈判中能够提取更高的剩余,并且在不同买家预算分布下表现出良好的泛化能力。

📝 摘要(中文)

谈判是管理科学中的一种基本战略互动,涉及代理人试图达成协议并保护私人信息。本文分析了单一卖家与多个具有异质性预算的买家同时谈判的复杂场景,指出现有大型语言模型在经济决策方面的不足。为此,提出了一种基于可验证奖励的强化学习(RLVR)训练方案,通过将奖励函数与客观经济结果相结合,帮助卖家在市场探索与利润提取之间取得战略平衡。实验结果表明,经过训练的卖家能够显著提高其谈判技能,并在未见的买家谈判风格中保持策略的有效性。

🔬 方法详解

问题定义:本文旨在解决单一卖家在与多个买家谈判时的决策效率问题。现有方法在经济决策上存在明显不足,无法有效探索潜在的高价值买家。

核心思路:提出了一种基于可验证奖励的强化学习方法,通过将奖励函数与实际经济结果相结合,使得卖家在学习过程中自然而然地实现市场探索与利润提取的平衡。

技术框架:整体架构包括数据收集、模型训练和策略评估三个主要模块。首先,通过模拟环境收集买家出价数据,然后利用强化学习算法训练卖家模型,最后评估其在不同买家策略下的表现。

关键创新:最重要的技术创新在于将奖励机制与经济结果直接关联,突破了传统模型在决策时的局限,使得学习过程更加符合实际市场动态。

关键设计:在参数设置上,采用了动态调整的学习率和多阶段训练策略,损失函数设计上强调了经济效益,网络结构则结合了深度学习与强化学习的优势。

🖼️ 关键图片

fig_0
fig_1
fig_2

📊 实验亮点

实验结果表明,经过RLVR训练的卖家在谈判中提取的剩余显著高于现有前沿模型,具体提升幅度达到30%以上。同时,该模型在面对不同买家预算分布时,表现出良好的适应性和泛化能力。

🎯 应用场景

该研究的潜在应用场景包括电子商务、拍卖系统和供应链管理等领域,能够帮助卖家在复杂的市场环境中优化谈判策略,提高交易成功率和经济效益。未来,该方法还可能扩展到其他类型的多方博弈和决策问题中,具有广泛的实际价值。

📄 摘要(原文)

Negotiation is a fundamental strategic interaction in management science, characterized by agents attempting to reach agreements while protecting private information, such as reservation costs and hidden valuations. A prevalent yet complex scenario involves a single seller negotiating concurrently with multiple buyers, each possessing heterogeneous, private budgets. In such settings, constrained by a limited number of communication turns, the seller must balance exploring the broader market to discover the highest valuation with concentrating sufficient turns on a single target buyer to secure the best possible outcome. Our analysis reveals a significant gap in standard Large Language Models (LLMs): while these models are linguistically proficient, they fail to act as effective economic decision-makers. Specifically, they exhibit a failure to explore the buyer pool, often fixating on the current highest bid rather than strategically investigating the market to discover latent high valuations. In this paper, we propose a specialized training recipe using Reinforcement Learning from Verifiable Rewards (RLVR). By anchoring the reward function to objective economic outcomes, the strategic balance between market discovery and surplus extraction emerges natively through the learning process. Our results demonstrate that the trained seller undergoes a multi-stage strategic evolution, learning to leverage price anchoring and strategic probing to identify more profitable counterparties. The agent extracts a substantially higher surplus than frontier models by both improving its persuasive bargaining skills and consistently closing deals with high-value buyers. Finally, we show that our seller strategies generalize robustly to unseen buyer negotiation styles and budget distributions.