AI RESEARCH

SCOPE: Real-Time Natural Language Camera Agent at the Edge

arXiv CS.CL

ArXi:2606.02951v1 Announce Type: cross Deploying language-driven agents in robotics requires evaluations that reflect real-world task demands: natural-language instructions with reproducible outcomes. Such agents must connect language models to callable perception and control tools, and be assessed using deployment-critical metrics including latency, accuracy, and error modes.