Science

New research reveals that large language models struggle with everyday reasoning that relies on understanding unwritten social rules and contextual cues.

As conversational AI systems become increasingly complex, ensuring their reliability requires a shift towards systematic and automated quality assurance.

A new framework bridges the gap between natural language and robotic action, allowing robots to perform complex tasks based on spoken instructions.

This tutorial offers a unified approach to integrating reasoning capabilities into information retrieval, moving beyond simple pattern matching to address complex information needs.

New research shows artificial intelligence can generate burger recipes that satisfy human palates while prioritizing sustainability and nutrition.

Researchers have developed a new method for creating increasingly complex reasoning problems to better train artificial intelligence systems.

New research demonstrates how leveraging human physiological data and off-policy evaluation can significantly improve the performance and usability of reinforcement learning agents in collaborative robotic systems.

A new framework uses intelligent software to automatically build comprehensive databases from scientific papers, accelerating materials science research.

A new benchmark assesses how well autonomous agents can independently arrive at established scientific findings, revealing significant hurdles to automating the full research cycle.

Researchers have developed a model-based control framework to navigate the complexities of high-degree-of-freedom continuum soft robots.