Science

A new review examines the current state of automated testing methods for task-based chatbots and highlights the challenges in ensuring their reliability.

New research demonstrates that equipping AI agents with curated skills dramatically boosts performance across diverse tasks, offering a significant leap beyond simple prompt engineering.

New research reveals that the effectiveness of AI companions in alleviating loneliness is heavily influenced by individual attachment styles and age groups.

A new framework translates natural language instructions into executable manufacturing plans, promising more adaptable and intelligent production systems.

A new framework improves how multiple AI agents learn and collaborate by enabling them to build and share a unified understanding of their environment.

A new framework balances performance and efficiency for deploying large AI models in real-world embodied systems.

A new framework allows robots to acquire complex manipulation skills simply by observing human demonstrations in video, bypassing the need for time-consuming and expensive robot-specific training.

Researchers present X-SYS, a comprehensive architecture designed to bridge the gap between explainable AI research and real-world application.

A new approach combines learned movement models with real-time optimization to enable robot manipulators to plan safe and efficient trajectories.

A new machine learning technique accurately identifies the size and charge of polycyclic aromatic hydrocarbons in space by analyzing their infrared light signatures.