CCTest · Blog
GMA Puts Mobile Agents Through More Realistic, Complex Workflows
Evaluation & Benchmarks
cctest.ai

GMA Puts Mobile Agents Through More Realistic, Complex Workflows

A new benchmark called GMA expands mobile-agent evaluation with seven open-source-based apps and 300 tasks ranging from atomic actions to multi-step workflows. Its results show that current agents struggle as complexity rises, while harness choices such as context retention and explicit state tracking can improve some demanding tasks.

Read more
CCTest · Blog
Texas Freezes Flock Camera Funding as AI Surveillance Faces Bipartisan Pushback
Policy & Regulation
cctest.ai

Texas Freezes Flock Camera Funding as AI Surveillance Faces Bipartisan Pushback

Texas Governor Greg Abbott has frozen state spending on additional Flock automatic license plate recognition cameras after an investigation reported more than $30 million in state spending. The decision highlights growing concerns about privacy, data sharing, and oversight of AI-enabled surveillance.

Read more
CCTest · Blog
TacForcing Brings Execution-Time Touch Feedback to Robot Policies
Robotics & Physical AI
cctest.ai

TacForcing Brings Execution-Time Touch Feedback to Robot Policies

TacForcing is a streaming action-generation framework that lets vision-language-action policies use tactile feedback as actions are being executed. It replaces a separate high-frequency reactive controller with a streaming action expert and reports stronger average success on simulated and real contact-rich tasks.

Read more