Related papers: AI-Powered Assistant for Long-Term Access to RHIC …
Recent highlights from Brookhaven National Laboratory and the Relativistic Heavy Ion Collider (RHIC) are reviewed and discussed. Topics include: Discovery of the strongly interacting Quark Gluon Plasma (sQGP) in 2005; RHIC machine operation…
The rise of Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG) has rapidly increased the need for high-quality, curated information retrieval datasets. These datasets, however, are currently created with off-the-shelf…
We address the challenge of multi-agent cooperation, where agents achieve a common goal by cooperating with decentralized agents under complex partial observations. Existing cooperative agent systems often struggle with efficiently…
We present Dynamic ReAct, a novel approach for enabling ReAct agents to efficiently operate with extensive Model Control Protocol (MCP) tool sets that exceed the contextual memory limitations of large language models. Our approach addresses…
Retrieval augmented generation (RAG) has become the standard in long context question answering (QA) systems. However, typical implementations of RAG rely on a rather naive retrieval mechanism, in which texts whose embeddings are most…
Catalysts are essential for accelerating chemical reactions and enhancing selectivity, which is crucial for the sustainable production of energy, materials, and bioactive compounds. Catalyst discovery is fundamental yet challenging in…
The large set of technical documentation of legacy accelerator systems, coupled with the retirement of experienced personnel, underscores the urgent need for efficient methods to preserve and transfer specialized knowledge. This paper…
This paper investigates the potential of AI models, particularly large language models (LLMs), to support knowledge exploration and augment human creativity during ideation. We present "Latent Lab" an interactive tool for discovering…
The Relativistic Heavy Ion Collider (RHIC) came online in 2000, and the last three years have provided a wealth of new experimental data and theoretical work in this new energy frontier for nuclear physics. The transition from quarks and…
Recent advancements in artificial intelligence (AI) applications within aerospace have demonstrated substantial growth, particularly in the context of control systems. As High Performance Computing (HPC) platforms continue to evolve, they…
We present Claw AI Lab, a lab-native autonomous research platform that advances automated research from a hidden prompt-to-paper pipeline into an interactive AI laboratory. Rather than centering the system around a single agent or a fixed…
The "AI Scientist" paradigm is transforming scientific research by automating key stages of the research process, from idea generation to scholarly writing. This shift is expected to accelerate discovery and expand the scope of scientific…
Document redaction is a crucial process in various sectors to safeguard sensitive information from unauthorized access and disclosure. Traditional manual redaction methods, such as those performed using Adobe Acrobat, are labor-intensive,…
Understanding and extracting structured insights from unstructured documents remains a foundational challenge in industrial NLP. While Large Language Models (LLMs) enable zero-shot extraction, traditional pipelines often fail to handle…
AI agents have seen widespread adoption in information retrieval for scientific research, giving rise to tools such as Deep Research. However, existing retrieval agents mainly rely on keyword- or embedding-based methods. While effective at…
A fundamental tension exists between the demand for sophisticated AI assistance in web search and the need for user data privacy. Current centralized models require users to transmit sensitive browsing data to external services, which…
AI evaluations have become critical tools for assessing large language model capabilities and safety. This paper presents practical insights from eight months of maintaining $inspect\_evals$, an open-source repository of 70+…
In low- and middle-income countries (LMICs), a significant proportion of medical diagnostic equipment remains underutilized or non-functional due to a lack of timely maintenance, limited access to technical expertise, and minimal support…
High Energy Physics (HEP) experiments like BESIII produce petabyte-scale data. Extracting physics results requires complex workflows (simulation, reconstruction, statistical analysis, etc.) that traditionally take experts months or years.…
Retrieval-Augmented Generation (RAG) has shown significant improvements in various natural language processing tasks by integrating the strengths of large language models (LLMs) and external knowledge databases. However, RAG introduces long…