arXiv cs.MA· Xinyu Wang, Andres Fielbaum·· 11 小时前AI 评分36
强制披露下如何评估网约车调度政策：用自利 LLM 司机智能体做实验
When Disclosure Is Compulsory: Evaluating Ride-Hailing Rebalancing Policies with Self-Interested LLM Driver Agents
AI 导读
研究用自利 LLM 司机智能体评估网约车调度政策，测试 Claude Haiku 5.5 与 Jev 在规则未公开（N）和按欧盟 Platform Work Directive 详细程度公开（L）两种条件下的表现。
正文 · 原文
Abstract: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.
| Subjects: | Multiagent Systems (cs.MA); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.41132 [cs.MA] |
| (or arXiv:2610.41132v1 [cs.MA] for this version) | |
| https://doi.org/10.48550/arXiv.2610.41132 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Xinyu Wang [view email]
[v1]
Fri, 30 Oct 2026 01:37:16 UTC (772 KB)
来源：arXiv cs.MA · arxiv.org