Survey Maps How Narrative Theory Shapes LLM Story Generation and Understanding
A survey in Artificial Intelligence Review categorises narrative theory-driven large language model methods and finds generation tasks lag behind understanding ...
Tag: Artificial Intelligence Review
Large Language Models Are Learning to Reason About Buildings, Review Finds
A systematic review of 76 studies finds large language models evolving from passive text processors into active cognitive partners for ...
Survey maps how machine learning exploits privileged information
A new survey reviews 107 papers on Learning Under Privileged Information and proposes a unified taxonomy of models and integration ...
Survey maps how LLM agents moved from single tool calls to multi-tool orchestration
A new open-access survey in Artificial Intelligence Review organizes research on LLM agents around six dimensions of multi-tool orchestration, from ...
Brain Foundation Models Shift From Borrowed AI Designs to Neuro-Native Architectures
A review in Artificial Intelligence Review maps how EEG foundation models evolved from borrowed language- and vision-model architectures between 2021 ...
How Retrieval-Augmented Generation Is Rewiring What AI Knows
A new survey in Artificial Intelligence Review maps the evolution of retrieval-augmented generation from simple retrieve-then-read pipelines to agentic systems, ...
New Taxonomy Maps the Entire Landscape of Retrieval-Augmented AI Systems
A new survey in Artificial Intelligence Review organizes the fast-moving field of retrieval-augmented generation into a four-axis taxonomy spanning efficiency, ...
Horse Herd Optimization Algorithm Gains Ground as a Flexible Problem-Solving Tool
A new review in Artificial Intelligence Review charts four years of development of the Horse Herd Optimization Algorithm, a nature-inspired ...
Hinton’s Forward-Forward Algorithm Gets a Hyper-Parameter Tune-Up That Closes the Accuracy Gap
A new study shows that automated metaheuristic hyper-parameter optimization substantially boosts the accuracy of Hinton's memory-efficient Forward-Forward training algorithm across ...
AI Agents Are Being Graded Wrong: Landmark Audit Finds No Benchmark Controls All Key Threats
A systematic survey of 259 studies finds that none of seventeen prominent AI agent benchmarks jointly controls data contamination, non-determinism, ...
-
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!