18 citations · 39 across the 41 of their papers we have counts for
14 papers · 1 filter
LLM Agents as Resilience Engineers for Scientific Applications
Hai Duc Nguyen, Tekin Bicer, Kyle Chard +2
Efficient checkpoint/restart support is essential for resilient HPC scientific applications, but implementing it requires substantial expertise: developers must identify recoverabl…
Reputation as Community Memory for the Agentic Web
Ryan Chard, Gus Ellerm, Alexander Brace +4
Agents can now externalize experience into memory, consolidating historical traces into semantic knowledge and procedural shortcuts that persist between sessions. Such memory is ty…
COMPASS: Steering Distributed Vector Search with Scientific Knowledge Graphs
Song Young Oh, Amal Gueroudji, Seth Ockerman +5
Vector databases use hashing to partition data across "shards," logical units for distributed execution. This placement, however, destroys semantic locality, forcing each query int…
ExaServe: Large-Scale LLM Serving on Exascale HPC Systems
Wenyi Wang, Shu Shi, Yadu Babuji +2
Cloud-native LLM serving frameworks have made deployment routine in data centers, yet deploying them on leadership-class supercomputers remains an engineering challenge requiring s…
Avatar: Toward Autonomous End-to-End Orchestration of Scientific Workflows using LLMs
Suman Raj, Hai Duc Nguyen, Haochen Pan +3
Scientific workflow management (WMSs) systems automate execution, yet orchestrate using fixed, hand-tuned rules. LLM agents promise more autonomous orchestration, but it remains un…
Diamond Agent: Agentic Control of Federated HPC Resources as a Service
Haotian Xie, Junlin Chen, Mingkai Zheng +9
Efficiently aggregating and orchestrating computing power across heterogeneous clusters for HPC workflows faces four practical challenges: preserving workflow context across indepe…
Interpreting Language Model Hidden States at Scale
Jordan Pettyjohn, Mansi Sakarvadia, Nathaniel Hudson +3
Lens methods interpret large language models (LLMs) by mapping intermediate activations to the output vocabulary, revealing how next-token predictions develop through the network.…
Toward Trustworthy Autonomous Science: A Two-Year Community Roadmap
Rafael Ferreira da Silva, Milad Abolhasani, Peter Beaucage +25
One year ago, the AISLE roadmap argued that autonomous laboratories operated as isolated islands and proposed a grassroots network organized around five critical dimensions. The fi…
Towards Transparent Checkpointing with AI-driven Code Generation
Hai Duc Nguyen, Tekin Bicer, Kyle Chard +2
Adding reliable checkpoint/restart support to an MPI scientific application is a time-consuming expert effort that requires deep knowledge of both the application and resilience. W…
StreamGuard: Low-Overhead Resilience for Real-time HPC Data Streams
Hai Duc Nguyen, Bogdan Nicolae, Tekin Bicer +4
Real-time scientific workflows operate on continuous data streams and must produce timely, high-quality results despite executing on complex, failure-prone infrastructure. Hardware…
When More Cores Hurts: The Vector Database Scaling Paradox in HPC
Seth Ockerman, Song Young Oh, Amal Gueroudji +12
Vector databases have been designed and optimized for cloud environments; however, emerging scientific AI workloads (e.g., molecular search, meteorological trajectory detection, an…
Beyond Fixed Budgets: Characterizing the Inelasticity and Limitations of Tree-of-Thought Reasoning Strategies
Atkia Mahila, Avinash Maurya, M. Mustafa Rafique +1
Tree of Thought (ToT) search has become a promising direction for improving the reasoning capabilities of large language models, but deploying these methods in practice raises a qu…
Icicle: Scalable Metadata Indexing and Real-Time Monitoring for HPC File Systems
Haochen Pan, Ryan Chard, Song Young Oh +7
Modern HPC file systems can contain billions of files and hundreds of petabytes of data, making even simple questions increasingly intractable to answer. Traditional file system ut…
Scalable Cross-Facility Federated Learning for Scientific Foundation Models on Multiple Supercomputers
Yijiang Li, Zilinghan Li, Kyle Chard +4
Artificial Intelligence for scientific applications increasingly requires training large models on data that cannot be centralized due to privacy constraints, data sovereignty, or…