Science

Understanding why AI coding agents fail is crucial for reliable software development, and this research introduces a method for turning complex execution data into actionable insights.

A new benchmark assesses how well large language models can automate the critical task of analyzing cybersecurity incidents.

A new framework details how to reliably orchestrate complex AI tasks across distributed systems, moving beyond simple requests to dynamic, interconnected agent interactions.

A new survey reveals that concerns among AI researchers center on near-term societal impacts, challenging common narratives about existential threats.

Current AI systems prioritize avoiding liability during mental health crises, but a new approach focuses on empowering users and providing constructive assistance.

A new framework leverages artificial intelligence to help urban transportation systems adapt to the growing risks of climate change and extreme weather events.

The growing use of artificial intelligence in weather and climate prediction presents both opportunities and risks, potentially exacerbating existing global inequalities.

Large language models are increasingly resolving ambiguous concepts into single interpretations, potentially diminishing the benefits of open-ended understanding.

A new study applies probabilistic machine learning to analyze the stopping times within the famous unsolved Collatz problem, revealing underlying statistical patterns.

New research demonstrates how sequence modeling techniques can bolster reinforcement learning agents against the challenges of unreliable data and incomplete information.