Scoping review maps how generative AI is reshaping education research
A scoping review of 189 empirical studies from four leading educational technology conferences finds generative AI research in education surged ...
Tag: multi-agent systems
Autonomous AI framework detects and restores grid faults in smart distribution networks
An AI framework combining supervised learning, autoencoder anomaly detection and a multi-agent system detected known and unseen faults in a ...
Evacuation modelling review maps 53 studies shaping safer building design
A systematic review of 53 studies finds agent-based modelling and cellular automata dominate evacuation simulation, while earthquake, residential and vulnerable-population ...
AI Agents Get Personalities: Scientists Propose Big Five Traits as Design Parameters
Researchers propose treating Big Five personality dimensions as tunable behavioral parameters in multi-agent AI systems, a testable framework rather than ...
Hybrid multi-agent model links capacity pricing and ancillary services in Chinese market simulation
A hybrid multi-agent modeling framework jointly optimizes capacity pricing and ancillary-service dispatch, improving matching, cost, and reserve outcomes in simulated ...
Systematic review maps AI robotics advances and persistent challenges
A PRISMA-based systematic review of 119 studies from 2018 to 2026 maps AI and robotics applications across industries, alongside challenges ...
AI Guardrails for Factories: Architecture Keeps LLMs From Unsafe Plant Actions
A four-layer multi-agent architecture confines LLM reasoning to an observation-only role and validates every proposal against plant engineering diagrams before ...
Adaptive diffusion model sharpens multi-agent trajectory prediction for autonomous driving
A new conditional diffusion framework called CDJMP predicts multi-agent vehicle trajectories with state-of-the-art accuracy while cutting inference time to under ...
LLM-Powered Search Engine Unifies China’s Fragmented Public Data Portals
Researchers built CN-PDS, an LLM-based search system that consolidates and enriches metadata from 148 of China's decentralized public data portals, ...
Emotion-aware multi-agent reinforcement learning boosts customer service dialogue performance in new study
A new open-access study reports that a multi-agent reinforcement learning framework combined with bio-inspired hyperparameter optimization outperformed comparison models on ...
-
Mothers who receive childcare support from maternal grandparents show more parental warmth, finds NTU Singapore study
-
University of Seville Breaks 120-Year-Old Mystery, Revises a Key Einstein Concept
-
Bee body mass, pathogens and local climate influence heat tolerance
-
Researchers record first-ever images and data of a shark experiencing a boat strike
-
Groundbreaking Clinical Trial Reveals Lubiprostone Enhances Kidney Function
Embark on a thrilling journey of discovery with Scienmag.com—your ultimate source for cutting-edge breakthroughs. Immerse yourself in a world where curiosity knows no limits and tomorrow’s possibilities become today’s reality!