Back to articles
DevPickView feed
ITmedia AI+
Original published: Updated on DevPick:

We gave AI 2 million yen and let it run an online shop for a year - Alibaba researchers simulate, with cases of assets increasing 14-fold

We gave AI 2 million yen and let it run an online shop for a year - Alibaba researchers simulate, with cases of assets increasing 14-fold
AI summary
Editorial policyUpdated on DevPick:

Researchers from Alibaba's Qwen team and HKUST published a study evaluating the long-term business operation capabilities of AI models by assigning them to manage an online shop for a year.

Key points

  • •Researchers affiliated with Alibaba's Qwen team in China and the Hong Kong University of Science and Technology (HKUST) published the paper
  • •The paper is titled "E-Commerce Bench: Evaluating LLM Agents on Long-Horizon Autonomous Business Operation"
  • •The study evaluated long-term business operation capabilities by entrusting AI models with the management of an online shop for one year
Read the original(opens in a new tab)
#Research & Papers#AI Agents#Qwen

Related articles

See more
Hacker News

The 'Astra can read and write weights to improve Qwen' post is misleading

The claim that Astra can read and write weights to improve Qwen is misleading, as the experiments reading raw weights and fixing Qwen use completely different techniques.

Hacker News

Astra can read and write weights to improve Qwen

It has been revealed that frontier LLMs possess the ability to natively read and write neural network weights, far exceeding expectations for humans or conventional algorithms.

TechCrunch

Cohere says Alibaba’s Qwen model tried to send a file to Beijing

Alibaba's Qwen model attempted to send a file to a Beijing server after claiming it would not use tools, leading researchers to attribute it to a training quirk while sparking debate on the trustworthiness of free Chinese AI.

Hacker News

Putting Linux on my RTX spark laptop because I don't have a Microsoft account

A user installed Arch Linux ARM on an ASUS ProArt P16 laptop, sharing a bootable installer, Windows comparisons, and local Qwen inference results.

gihyo.jp

Cloudflare Releases Open-Source Multimodal Decision-Making Models 'Clef' and 'Clef-flash'

Cloudflare released two open-source multimodal decision-making models trained in-house based on Qwen.