LLM代理选货主导致运输市场集中，平台信息设计可有效缓解。
When Shippers Become Algorithms: Candidate Exposure, Information Design, and the Concentration of LLM-Mediated Freight Markets
- 用大模型模拟50个货主，通过排名列表选择承运商，发现所有模型首推同一承运商。
- 当展示承运商超过10个时，市场集中度急剧上升，最高达76%的订单被单一承运商获取。
- 公开每日剩余运力可降低集中度30%，显著提升货主收益，优于其他设计手段。
货主正将承运商选择权交给大语言模型（LLM）代理。我们研究这种委托对货运匹配市场的影响及平台设计如何控制风险。通过基于代理的仿真，使用来自OpenAI（GPT）、Anthropic（Claude）和Google（Gemini）的商用大模型构建50个货主代理，为30天的整车运输需求采购运力。市场遵循数字货运匹配规则：每单按货主排序列表逐级发送（瀑布式招标），承运商有每日运力上限，现货价格随拥堵变化，承运商评分随交易累积。研究发现三个风险与一种有效应对策略：各模型在首日即收敛至同一首选承运商，其获单率高达76%；平台决定货主可见候选数量，当候选数超过约10个时，集中度迅速上升，且不同市场中主导承运商差异显著；即使展示真实质量而非评分估计，也未改变集中度水平或波动性（因质量仅影响可见性，不影响实际履约）。相反，公开承运商每日剩余运力使集中度下降三分之一，货主盈余翻倍，而供应商多样性、列表顺序随机化及热度显示无明显效果。平台信息设计，先于模型选择或监管，是关键调控杠杆。
原文摘要 · Abstract (English)
Shippers are beginning to delegate carrier selection to large language model (LLM) agents. We ask what such delegation does to a freight matching market, and which platform design choices contain it. We carried out agent-based simulations in which fifty shipper agents, built on commercial LLMs from OpenAI (GPT), Anthropic (Claude), and Google (Gemini), procure truckload capacity for thirty days. The market implements the rules of digital freight matching: each load is offered down the shipper's ranked list of carriers (waterfall tendering), carriers have daily capacity limits, spot prices respond to congestion, and carrier ratings accumulate with transactions. We found three risks and one remedy that works. Agents converged at once: for a fixed sampled carrier population, the same carrier was the modal first choice of every model on day one, attracting up to 76% of requests. Because each agent picks from its own randomly drawn list of displayed candidates, the platform controls how many options each shipper sees; concentration rose steeply once lists exceeded about ten carriers, with the onset differing across models. Which carriers ended up dominant varied widely from one sampled market to another, and displaying true quality instead of estimated ratings changed neither the level nor this variability (by design, quality affects only what agents see, never delivery outcomes). Against these risks, disclosing each carrier's remaining daily capacity cut concentration by a third and doubled shipper surplus, while vendor diversification, list-order randomization, and popularity display showed no clearly detectable effect. Platform information design, ahead of model choice or model regulation, is the lever that works.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。