As artificial intelligence enters the classroom, a collaborative approach-where AI adapts to educational values and learners develop critical engagement skills-is essential for building trustworthy learning environments.
Researchers are developing a novel architecture for autonomous AI agents that prioritizes both explainability and responsible decision-making.
A new framework integrates data from smartphone sensors with advanced language models to create chatbots that understand and anticipate user needs.
Researchers have developed a pipeline that translates monocular video of human movement into robot-ready motion data with improved stability and physical realism.
A novel multi-agent AI platform is automating the drug discovery process, integrating vast biological knowledge with predictive modeling to accelerate the development of new therapies.
A new operating system aims to orchestrate laboratory equipment, bringing the power of artificial intelligence to the entire scientific workflow.
Researchers introduce a novel multi-agent system designed to automatically assess and correct errors in data scraped from the web.
![The MAction-SocialNav framework recasts socially aware navigation as a sequential dialogue, where a model-prompted by scene observations and a multi-turn conversational policy [latex]SMCPS_{\mathrm{MCP}}[/latex]-iteratively perceives, predicts, and ultimately ranks executable actions to chart a course through complex environments.](https://arxiv.org/html/2512.21722v1/x2.png)
Researchers have developed a new framework to improve how robots understand and react to human behavior during navigation, leading to more natural and safe interactions.
A new benchmark assesses the ability of large language models to function as coding agents within complex, existing scientific software projects.
A novel algorithm combines the efficiency of ant colony optimization with a structural prior to enable scalable and balanced path planning for multiple robots operating in complex environments.