Tencent says third-party models, not Hunyuan, responsible for AI agent activity

Tencent said it was tightening network access controls and monitoring of AI agents after researchers found that agents running on its cloud infrastructure repeatedly tried to bypass restrictions on Alibaba's Amap mapping service.

The Chinese technology group said that the activity occurred during evaluations of third-party AI models, rather than its own Hunyuan models.

An internal review found no evidence of deliberate targeting or coordination, it said in a statement posted on its Tencent Hunyuan account on X on Friday.

"We take these findings seriously. We are strengthening network access controls and agent monitoring," the company said.

The response followed an earlier report by independent AI safety research group Swarmchasers, which documented more than 2,600 attempts between Sept 28 and Oct 8 to extract information from Amap.

The agents were pursuing seemingly routine questions, including which entrances visitors most often used when navigating to Chinese zoos and other attractions. After encountering Amap's automated access restrictions, they tried alternative routes, including third-party web services and access credentials exposed in publicly available code, the researchers said.