Results 81 to 90 of about 429 (159)

An LLM Framework for Regional Climate Services: Integrating Climate Knowledge and Ensemble Projections

open access: yesJournal of Geophysical Research: Machine Learning and Computation, Volume 3, Issue 4, August 2026.
Abstract Recent advances in generative AI have enabled the integration of scientific knowledge into natural language interfaces. However, existing large language models (LLMs) lack domain‐specific expertise and cannot directly utilize simulation data essential for risk assessment.
D. Matsuoka   +12 more
wiley   +1 more source

Thinking Is Not Enough: The B* Expansion Technique for Enhancing Autonomous LLM Agents

open access: yesExpert Systems, Volume 43, Issue 8, August 2026.
ABSTRACT Most autonomous agents built on large language models (LLMs) focus on improving internal reasoning while assuming a fixed and complete set of primitive actions. In this work, we challenge this assumption and introduce the B*$$ {B}^{\ast } $$ expansion technique, an action‐centric method that enables agents to iteratively construct new actions ...
Sebastián Andrés Mayorquín Posadas   +1 more
wiley   +1 more source

AI Agent for Hydrologic Modeling: Definition, Development, and Application

open access: yesGeophysical Research Letters, Volume 53, Issue 13, 16 July 2026.
Abstract Hydrologic modeling supports flood forecasting and water resources management, but complex preprocessing, parameterization, and configuration limit broader use. This study defines a six‐level framework for artificial intelligence (AI)‐agent autonomy in hydrologic modeling and develops a Level‐4 agent, powered by large language models, that ...
Songkun Yan   +11 more
wiley   +1 more source

Interface‐Engineered Binary Framework Composites: Advancing Porous Materials for Precision Medicine

open access: yesAdvanced Materials Interfaces, Volume 13, Issue 13, 7 July 2026.
Binary framework composites integrate two complementary porous architectures into a unified platform, enabling multifunctional design, enhanced structural tunability, and improved physicochemical performance. By combining high surface area, ordered porosity, interfacial synergy, and versatile functionalization, these hybrid materials offer new ...
Navid Rabiee   +3 more
wiley   +1 more source

An Open‐Source Systematic Reviews Integrated System (OSSYRIS) – Streamlining Processes and Standardising Data Structures

open access: yesCochrane Evidence Synthesis and Methods, Volume 4, Issue 4, July 2026.
ABSTRACT Introduction Carrying out a systematic review (SR) of the literature entails a high workload and encompasses a variety of very different tasks. The emergence of artificial intelligence tools has brought further opportunities to improve the efficiency and reliability of SRs.
Xavier Bosch‐Capblanch   +8 more
wiley   +1 more source

Home - About - Disclaimer - Privacy