Science

New research demonstrates that artificial intelligence can accurately anticipate human actions and their timing with remarkably little training data.

A novel approach combines statistical analysis with agent-based modeling to accurately forecast how large language models will perform on diverse tasks.

This comprehensive survey traces the evolution of communication strategies in multi-agent systems, from basic reinforcement learning to sophisticated language-based coordination.

A large-scale analysis of open-source Android and iOS projects reveals how AI coding agents are performing in real-world development workflows.

A new framework allows robots to dynamically search for missing objects while planning complex tasks, boosting reliability in unpredictable environments.

Researchers have developed an autonomous agent, LawThinker, designed to conduct deep legal research and reasoning within the complex and ever-changing landscape of judicial proceedings.

A new framework leverages intelligent agents to automate robot training, overcoming the bottlenecks of traditional reinforcement learning methods.

A new framework aims to imbue artificial intelligence with the ability to adapt not just its knowledge, but also the very processes it uses to reason and solve problems.

New research explores how intelligent, embodied AI agents can improve collaboration and learning in hands-on workplaces.

New research reveals that trust in AI-assisted advice isn’t just about accuracy, but crucially depends on who-human or machine-corrects any mistakes.