Related papers: AI-Powered Assistant for Long-Term Access to RHIC …
The rapidly growing popularity of adopting Artificial Intelligence (AI), and specifically Large Language Models (LLMs), is having a widespread impact throughout society, including the academic domain. AI-supported research has the potential…
The Relativistic Heavy Ion Collider (RHIC) at Brookhaven has completed nearly two years of successful commissioning and operation. The control system is briefly reviewed and its contribution to the RHIC effort is analyzed, with emphasis on…
The HENP computing facility at Brookhaven National Laboratory supports both the Relativistic Heavy Ion Collider (RHIC) and US involvement in the ATLAS LHC experiment. The facility includes 150 TBytes of centralized online (disk) storage,…
Generative AI, especially through large language models (LLMs), is transforming how technical knowledge can be accessed, reused, and extended. PETSc, a widely used numerical library for high-performance scientific computing, has accumulated…
We present Machine Assistant with Reliable Knowledge (MARK), a retrieval-augmented question-answering system designed to support student learning through accurate and contextually grounded responses. The system is built on a…
The movement of the Relativistic Heavy Ion Collider (RHIC) through its various states (eg. injection, acceleration, storage, collisions) is controlled by an application called the Sequencer. This program orchestrates most magnet and…
Large-scale machines like particle accelerators are usually run by a team of experienced operators. In case of a particle accelerator, these operators possess suitable background knowledge on both accelerator physics and the technology…
Effective knowledge management is critical for preserving institutional expertise and improving the efficiency of workforce training in state transportation agencies. Traditional approaches, such as static documentation, classroom-based…
The complexity and sheer volume of information encompassing documents, papers, data, and other resources from large-scale experiments demand significant time and effort to navigate, making the task of accessing and utilizing these varied…
The rapid advancements in Generative AI and Large Language Models promise to transform the way research is conducted, potentially offering unprecedented opportunities to augment scholarly workflows. However, effectively integrating AI into…
Designing a generalist scientific agent capable of performing tasks in laboratory settings to assist researchers has become a key goal in recent Artificial Intelligence (AI) research. Unlike everyday tasks, scientific tasks are inherently…
At the Brookhaven National Laboratory, experimental efforts with heavy-ion accelerators started at the AGS synchrotron in 1984 and then at the Relativistic Heavy Ion Collider (RHIC) in 1991. This chapter of a future book describes how…
We present an open-source pipeline for generating a \emph{living review} of artificial intelligence (AI) and machine learning (ML) applications in accelerator physics and technologies. Traditional review articles provide static snapshots…
High-quality scientific review and perspective papers require substantial time and effort, limiting researchers' ability to synthesize emerging knowledge. While Large Language Models (LLMs) leverage AI Scientists for scientific workflows,…
Computational reproducibility is central to scientific credibility, yet verifying published results at scale remains costly. We develop an AI-assisted workflow for automated full-paper replication -- retrieving materials, reconstructing…
The rapid development of artificial intelligence (AI), marked by breakthroughs like 'AlphaEvolve' and 'Gemini Deep Think', is beginning to offer powerful new tools that have the potential to significantly alter the research practice in many…
We discuss long-term preservation of and access to relational databases. The focus is on national archives and science data archives which have to ingest and integrate data from a broad spectrum of vendor-specific relational database…
Next-generation High Energy Physics (HEP) experiments will generate unprecedented data volumes, necessitating High Performance Computing (HPC) integration alongside traditional high-throughput computing. However, HPC adoption in HEP is…
The development of large language models (LLMs) has significantly enhanced the capabilities of multimodal LLMs (MLLMs) as general assistants. However, lack of user-specific knowledge still restricts their application in human's daily life.…
The emergence of Large Language Models (LLMs) has significantly advanced solutions across various domains, from political science to software development. However, these models are constrained by their training data, which is static and…