Understand this story
On November 2, 2026, Zhiyuan Robotics launched the "Robot Workers Can't Stop" 24-hour convenience store challenge livestream at an operating convenience store in Xuhui District, Shanghai. Six Jingling G2 robots collectively took up posts, divided into 4 shifts to handle tasks such as greeting customers, making coffee, deli service, picking and restocking goods, and table cleaning, while undergoing real-time supervision by the entire internet. According to a same-day report by Shangguan News, as of 2:30 p.m. that day, the six robots had been on duty for 4.5 hours and cumulatively completed 337 tasks, including receiving customers 116 times, delivering and retrieving 84 items, and making coffee 30 times. Another Shangguan News report stated that the six robots share Zhiyuan's embodied Agent framework Genie Master as their scheduling and learning hub, summarizing successful and failed trajectories daily and storing them in long-term memory, and converting effective adjustments into training data. The challenge is currently still ongoing.
AI-generated from public reports
Latest development · Report
Six AgiBot Genie G2 robots enter a Shanghai convenience store, taking on a 24-hour real-world work challengeDevelopments
1 confirmed developments
AgiBot launches 24-hour convenience store challenge livestream with 6 Elf G2 robots
Source:Shangguan News
Reports and discussion timeline
Browse reports and discussion by time. Their evidence levels remain distinct.
Nov 2
Leikeji
Six AgiBot Genie G2 robots enter a Shanghai convenience store, taking on a 24-hour real-world work challenge
On November 2, six AgiBot Genie G2 humanoid robots entered an operating convenience store in Xuhui, Shanghai, working continuously for 24 hours as greeters, baristas, stock clerks, and cleaners, under live online supervision from viewers across the internet. The six robots were centrally coordinated by the embodied Agent framework Genie Master, connecting task judgment, action execution, and result feedback through the Embodied Execution Protocol (EEP), and storing both successful and failed task trajectories in long-term memory to feed back into action policy optimization. This was the final real-world test following the release of AgiBot's AI WAVE series of technologies.
English text is being prepared.Related discussion
English text is being prepared. joined this discussion
This post contributes to heat; it is not a formal report or confirmed fact.
Shanghai Observer
Six AgiBot Genie G2 Humanoid Robots Work 24-Hour Shifts at a Shanghai Convenience Store
Starting at 10:00 on November 2, six AgiBot Genie G2 humanoid robots clocked in at a 24-hour convenience store in Xuhui, Shanghai, taking on roles including greeter, barista, stocker, cashier, and cleaner. They worked continuously for a full day, with the whole process livestreamed for viewers across the internet. On-site experience officers set up challenges such as handing over the wrong-sugar cola, disarranging shelves, and human roadblocks, and the robots responded through voice recognition, visual inventory checks, and path replanning. The six robots share AgiBot's embodied Agent framework Genie Master as their scheduling and learning hub; each day they summarize successful and failed trajectories and store them in long-term memory, converting effective adjustments into training data.
Shanghai Observer
AgiBot's 6 Genie G2 Robots Work 24-Hour Live-Streamed Shifts at a Convenience Store
AgiBot launched a 24-hour livestream at an operating convenience store in Xuhui District, where 6 Genie G2 robots took on tasks including greeting customers, making coffee, serving prepared food, picking and restocking goods, and cleaning tables, working in 4 shifts under real-time supervision by the entire internet. As of 2:30 p.m. yesterday, the 6 robots had been on duty for 4.5 hours and completed a total of 337 tasks, including greeting customers 116 times, delivering and retrieving 84 items, and making coffee 30 times. AgiBot previously released the GO-3 foundation model and the embodied intelligence agent "Genie Master," and together with Tsinghua University and Infinigence AI proposed a collective experience learning paradigm, validated in a cluster of 96 robots, where the success rate rose from 86.7% to 98.3% as the number of robots participating in training increased from 16 to 96.
English text is being prepared.
Six AgiBot Genie G2 Robots Take Up Posts at a Convenience Store, Challenging Continuous 24-Hour Operation
On November 2, AgiBot launched the "Robot Workers Can't Stop" 24-hour convenience store challenge livestream, with six Genie G2 robots collectively taking up posts, covering tasks such as greeting and reception, coffee preparation, prepared food service, picking and restocking, and tabletop cleaning. The challenge relies on the AgiBot GO-3 embodied foundation model and the Genie Master embodied Agent, focusing on testing the robots' long-duration operation, task execution, and autonomous response capabilities in complex environments, while exploring the feasibility of multi-robot collaborative operation.
English text is being prepared.Related discussion
English text is being prepared. joined this discussion
This post contributes to heat; it is not a formal report or confirmed fact.
Heat trend for this story
- Current
- 23
- Period peak
- 27 Nov 2 23:00
- 24-hour change
- —
Move the pointer or select the chart to inspect hourly heat. Use the left and right arrow keys with a keyboard.