智能体
arxiv.org ·
算法购物：智能体 AI 如何将人类启发式策略部署为代理消费者
arXiv 论文（econ.GN/cs.AI）研究消费者将购买决策委托给 LLM 作为代理消费者时的行为。作者提出 Tool-Lab，将产品属性置于需付费工具调用之后，对来自三家提供商的八个商用 LLM 追踪选择前的信息获取过程。结果显示：零成本下定价线索很少误导；在模糊目标提示下施加获取成本，LLM 会省略计算单价所需的诊断性属性，产生类似人类启发式的次优选择；具体目标提示则基本保持诊断性搜索与选择最优性。作者认为委托式 AI 购物中的营销启发式由店铺信息架构决定，而非 LLM 的固有缺陷。
AI推荐理由 arXiv 经济学与 AI 交叉方向新论文，提出 Tool-Lab 信息板过程追踪方法，在来自三家提供商的八个商用 LLM 上考察定价线索（just-below pricing、促销框架）对 AI 购物代理的影响。核心发现具有具体机制：零成本时定价线索很少误导；在模糊目标提示下引入信息获取成本，LLM 会省略计算单价所需的诊断性属性，做出类似人类启发式的次优选择；而具体目标提示基本保持诊断性搜索与选择最优性。作者据此认为委托式 AI 购物中的营销启发式受店铺信息架构支配，而非 LLM 固有缺陷。局限在于摘要未给出样本量、效应大小与统计细节，结论需以全文验证。
72
正文
Economics > General Economics
arXiv:2609.28372 (econ)
[Submitted on 23 Sep 2026]
Title:Shopping by algorithm: How agentic AI deploys human heuristics as a surrogate consumer
Authors:Davood Wadi, Yu Ma
View a PDF of the paper titled Shopping by algorithm: How agentic AI deploys human heuristics as a surrogate consumer, by Davood Wadi and 1 other authors
View PDF
HTML (experimental)
Abstract:Consumers increasingly delegate purchasing decisions to Large Language Models (LLMs) acting as surrogate consumers. Using "Tool-Lab," an adaptation of information-board process tracing that places product attributes behind costly tool calls, we examine how marketing pricing cues (i.e., just-below pricing and promotional framing) influence AI shopping agents. Across eight commercially deployed LLMs from three providers, we trace pre-choice information acquisition. Under zero cost, pricing cues rarely mislead. Imposing acquisition costs under a vague goal prompt leads LLMs to omit diagnostic attributes required to compute unit price and choose suboptimal choices resembling human heuristics. Relative to a specific goal prompt that mainly preserves diagnostic search and choice optimality, a vague goal prompt under constraints creates a search-mediated vulnerability. This research demonstrates that marketing heuristics in delegated AI shopping are governed by storefront information architecture, not necessarily immutable LLM flaws.
Subjects:
General Economics (econ.GN); Artificial Intelligence (cs.AI)
Cite as:
arXiv:2609.28372 [econ.GN]
(or
arXiv:2609.28372v1 [econ.GN] for this version)
https://doi.org/10.48550/arXiv.2609.28372
Focus to learn more
arXiv-issued DOI via DataCite (pending registration)
Submission history
From: Davood Wadi [view email]
[v1]
Wed, 23 Sep 2026 16:47:52 UTC (5,011 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled Shopping by algorithm: How agentic AI deploys human heuristics as a surrogate consumer, by Davood Wadi and 1 other authors
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
econ.GN
new
|
recent
| 2026-09
Change to browse by:
cs
cs.AI
econ
q-fin
q-fin.EC
References & Citations
NASA ADS
Google Scholar
Semantic Scholar
export BibTeX citation
Loading...
BibTeX formatted citation
×
loading...
Data provided by:
Bookmark
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data, Media
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv (What is alphaXiv?)
Links to Code Toggle
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub Toggle
DagsHub (What is DagsHub?)
GotitPub Toggle
Gotit.pub (What is GotitPub?)
Huggingface Toggle
Hugging Face (What is Huggingface?)
ScienceCast Toggle
ScienceCast (What is ScienceCast?)
Demos
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Related Papers
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
Author
Venue
Institution
Topic
About arXivLabs
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Which authors of this paper are endorsers? |
Disable MathJax (What is MathJax?)