When Disclosure Is Compulsory: Evaluating Ride-Hailing Rebalancing Policies with Self-Interested LLM Driver Agents

📄 arXiv: 2610.41132v1 📥 PDF

作者: Xinyu Wang, Andres Fielbaum

分类: cs.MA, cs.AI

发布日期: 2026-10-30


💡 一句话要点

利用自利型LLM代理评估强制披露下的网约车再平衡政策

🎯 匹配领域: 支柱九:具身大模型 (Embodied Foundation Models)

关键词: 网约车 再平衡政策 大型语言模型 强制披露 自利型代理 收益优化 政策评估

📋 核心要点

  1. 现有的网约车再平衡政策在强制披露下表现不一,影响平台和司机的收益。
  2. 本文提出利用自利型LLM代理模拟司机行为,比较反应型和预期型再平衡政策的效果。
  3. 实验结果显示,在强制披露下,预期型政策显著提高了司机收入和平台利润,且服务率提升明显。

📝 摘要(中文)

欧盟平台工作指令要求网约车平台以简单明了的语言披露自动决策的主要参数及其对司机行为的影响。本文比较了两种主要的再平衡政策:反应型政策(R)和预期型政策(A),并利用大型语言模型(LLM)代理模拟司机行为。研究发现,在规则披露后,司机更倾向于遵循平台的指示,尤其是在曼哈顿地区,拒绝搬迁的比例显著下降。尽管两种政策在完全合规下的利润相同,但在强制披露下,R政策的利润下降了3.7%,而A政策的利润保持不变。此研究为评估新要求下的再平衡政策提供了框架,并首次使用LLM代理进行分析。

🔬 方法详解

问题定义:本文旨在探讨在强制披露的情况下,网约车再平衡政策对司机和平台收益的影响。现有方法未能充分考虑规则披露对司机行为的影响,导致政策效果评估不准确。

核心思路:通过引入自利型大型语言模型(LLM)代理,模拟司机在不同政策下的决策过程,比较反应型和预期型政策的表现。设计的核心在于利用LLM对规则的理解能力,使其能够自主决策。

技术框架:研究采用三区域模型和曼哈顿区域进行实验,分别测试反应型政策(R)和预期型政策(A)。每个司机作为LLM代理,最大化自身净收入,评估在无规则和有规则情况下的表现。

关键创新:本文首次将LLM代理应用于网约车再平衡政策的评估,揭示了强制披露对政策效果的显著影响,尤其是在不同政策下的收益差异。

关键设计:实验中使用了Claude Haiku 5.5和Jev两种LLM,确保对规则的理解一致。通过对比不同政策下的司机收入、平台利润和服务率,分析了披露对再平衡策略的影响。实验结果显示,反应型政策在披露后利润下降,而预期型政策则保持稳定。

🖼️ 关键图片

fig_0

📊 实验亮点

实验结果表明,在曼哈顿地区,反应型政策的利润下降了3.7%,而预期型政策的利润保持不变。司机的收入在小模型下均有所提升,服务率提高了10至18个百分点,显示出强制披露对再平衡政策的深远影响。

🎯 应用场景

该研究为网约车平台在实施强制披露政策时的再平衡策略提供了理论依据,能够帮助平台优化决策,提高司机和用户的满意度。未来,类似的方法可以扩展到其他领域,如共享经济和自动驾驶等,具有广泛的应用潜力。

📄 摘要(原文)

The EU Platform Work Directive, to be transposed by December 2026, requires ride-hailing platforms to state in plain language the main parameters of their automated decisions and how a worker's behaviour affects them. Such rules are exactly what a large language model (LLM) can read, so drivers will be able to let one decide for them. We compare two main families of rebalancing policy once their rules are public: a reactive policy (R) that sends idle drivers to cover requests just lost, and an anticipatory policy (A) that plans moves on a demand forecast. Each driver is an LLM agent maximizing its own net income, given no rules (N) or the rules at the directive's level of detail (L). We test two LLMs, Claude Haiku 5.5 and Jev, which understand the rules equally well, in a three-zone model and in Manhattan. With the rules disclosed, drivers follow the platform more closely: in Manhattan, the share of relocation offers they decline falls from about four in five to one in four under both policies. Yet the effects differ by policy. For the platform, disclosure costs R 3.7% of its profit in Manhattan, as R now pays for moves drivers used to make for free, while A's profit is unchanged; the two policies, which tie on profit under full compliance, end 6.1% apart. For drivers, disclosure raises income in the small model under both policies and LLMs; for users, it raises the service rate there by 10 to 18 percentage points. In Manhattan, self-interested drivers also make A a win-win-win against full compliance, raising driver income, platform profit and service rate by 10 to 12% each. Rebalancing policies that perform equally well under full compliance can thus show opposite results under mandatory disclosure. The study offers a framework to evaluate such policies under the new requirement and is, to our knowledge, the first to do so with LLM agents.