Abstract-Large language models (LLMs) are increasingly being deployed with extended context windows ranging from 100K to 200K tokens, enabling applications involving long-document analysis, multi-source reasoning, and prolonged conversational interaction. Despite these developments, the practical reliability of long-context processing remains insufficiently understood. This study introduces KS-Probe (Probing Recall Over Boundaries and Extents), a benchmark framework developed to systematically evaluate context fidelity... view more..

Abstract-This paper presents EVA, an intelligent voice   controlled robotic assistant integrating speech recognition, ESP32-CAM vision, spatial memory and a multi-degree-of freedom robotic arm. The system combines perception, decision making and actuation through a modular architecture. Continuous listening, interrupt-driven control and asynchronous software enable responsive human–robot interaction. The robotic arm executes basic manipulation tasks while the vision module detects objects and supports contextual awareness.... view more..