This work presents an agentic architecture for large language models that could automate reasoning over structured scientific databases in chemistry and materials science, but this requires purpose-built agentic architectures not simply better models.
Abstract
Large language models (LLMs) could automate reasoning over structured scientific databases in chemistry and materials science, but this requires purpose-built agentic architectures, not simply better models. We present an agentic...
GenAI is accelerating computer science in nearly every way, but to truly realize the potential for this, the foundations for these workflows to be able to operate must be built.
Brian Suchy, Harry Wang, Yu-Hao Zhu et al.· 0 citations
Artificial intelligence (AI) is transforming scientific practice. What started as a passive data-analysis tool has become something closer to an active partner, now capable of generating hypotheses, planning experiments, and coordinating multi-step workflows. This manuscript explores how large language models (LLMs) an...
Graziella Orrú, Pietro Pietrini, Giuseppe Sartori· Forensic Sciences Research· 0 citations
Large language models (LLMs) are increasingly applied to molecular property prediction, but whether they encode notation-agnostic molecular representations or exploit surface-level string patterns re- mains untested. We present a dual-phase...
In June 2026, zbMATH Open has released an experimental search
option facilitating the translation of natural language queries into
faceted search commands, taking full advantage of the traditional
precise query language without requiring knowledge of its details.
O. Teschke· European Mathematical Societ...· 0 citations