Science

Researchers have created a benchmark demonstrating that AI agents can independently develop effective control policies for physical robots, often exceeding human-level performance.

A new study reveals that automatically generated code changes, while often accepted, can quietly introduce complexity and potential vulnerabilities into software projects.

A new evaluation of decentralized multi-robot SLAM systems reveals the critical trade-offs for autonomous mapping in challenging planetary analogue terrains.

A new machine learning framework accelerates the discovery of promising metal hydrides for efficient and scalable hydrogen storage.

As artificial intelligence reshapes work, a new study examines how productivity gains can subtly erode human skills and dignity.

A new library demonstrates the potential-and challenges-of combining traditional agent programming with the power of modern large language models.

A new study examines the impact of AI coding assistants on the quality and characteristics of pull requests, comparing them directly to human-authored contributions.

Researchers have developed a method that combines data-driven learning with inherent physical symmetries to accurately identify the governing equations of complex dynamical systems.

Researchers have developed a new technique to synthesize realistic human movements directly from user interaction logs, offering a powerful tool for understanding and improving user experience.

Researchers are leveraging the precision of optical tweezers to map the mechanical properties of active materials and biological tissues at the microscopic level.