PulseAugur
中
实时 13:02:17
English(EN) AI agents went shopping for TVs and laptops—and messed up nearly 50% of the time, study shows

Visa研究:AI代理近半数购物任务失败

Visa的最新研究显示,AI代理在购物任务方面存在困难,购买电视和笔记本电脑等商品的平均成功率仅为57%。由Google的Gemini (Aragon 4)和Meta的Making (Wonder)等先进模型驱动的代理表现最佳,成功率达到82%。Claude代理的成功率为76%,OpenAI代理为64%。该研究强调了AI代理在理解复杂的消费者动机和收集必要信息方面面临的挑战,表明尽管代理式商业正在迅速发展,但围绕信任、安全支付和责任的问题仍需解决。 AI

影响 突显了AI代理在购物等复杂现实世界任务方面的当前局限性,指出了未来在理解用户意图和安全交易方面的发展方向。

排序理由 关于AI代理在特定任务中表现的研究结果。[lever_c_demoted from research: ic=1 ai=0.7]

在 Fortune 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。 我们如何撰写摘要 →

Visa研究:AI代理近半数购物任务失败

本文如何被排名

Signal score
33 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
关于AI代理在特定任务中表现的研究结果。[lever_c_demoted from research: ic=1 ai=0.7]
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
product, other
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
Breaking (< 6h)
Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

  1. Fortune TIER_1 English(EN) · Jeff John Roberts ·

    AI代理购买电视和笔记本电脑——研究显示,近50%的交易出现失误

    In a first of its kind experiment, Gemini and Muse agents scored the highest when it come to carrying out tasks like buying a TV.