5 papers
An Agentic Orchestration of Atomistic Simulations
Rahul Somasundaram, Adela Habib, Khanh Dang +12
Atomistic simulations are central to materials design, but their execution involves complex, multi-step workflows that require significant human expertise. Here, we present an agen…
Chain-based Adaptive Reconfiguration Over Lattices for Hallucination Reduction
Joan Vendrell Gallart, Solmaz Kia, Russell Bent +1
We introduce CAROL (Chain-based Adaptive Reconfiguration Over Lattices), a probabilistic framework for test-time hallucination reduction in large language models. Rather than relyi…
Hierarchical Prompt-Domain Control and Learning for Resource-Constrained Agentic Language Models
Joan Vendrell Gallart, Russell Bent, Michael Grosskopf
Large Language Models are increasingly deployed inside agentic systems, where they must follow structured protocols, adapt to evolving states, and operate under memory, latency, an…
URSA: The Universal Research and Scientific Agent
Michael Grosskopf, Nathan Debardeleben, Russell Bent +10
Large language models (LLMs) have moved far beyond their initial form as simple chatbots, now carrying out complex reasoning, planning, writing, coding, and research tasks. These s…
A Partitioned Sparse Variational Gaussian Process for Fast, Distributed Spatial Modeling
Michael Grosskopf, Kellin Rumsey, Ayan Biswas +1
The next generation of Department of Energy supercomputers will be capable of exascale computation. For these machines, far more computation will be possible than that which can be…