Showing 1–50 of 192 results for author: Foster, I

Wrong but Useful: Trajectory Value Beyond Answer Correctness in Multi-Agent Messages

Authors: Chih-Hsuan Yang, Anjir Ahmed Chowdhury, Cheng-Hau Yang, Weijian Zheng, Fernando Llorente, Xiaolong Ma, Xinyang Li, Eliu A. Huerta, Ian T. Foster, Rajeev Thakur

Abstract: Multi-agent reasoning systems often use agreement, confidence, or automated scores to decide which messages should shape a final answer. Such filtering assumes that a message likely to be correct is also worth keeping. Yet a wrong answer can contain a useful decomposition, constraint, or scientific principle. We test this distinction with Diverse Hypothesis Deliberation (DHD), a controlled measure… ▽ More Multi-agent reasoning systems often use agreement, confidence, or automated scores to decide which messages should shape a final answer. Such filtering assumes that a message likely to be correct is also worth keeping. Yet a wrong answer can contain a useful decomposition, constraint, or scientific principle. We test this distinction with Diverse Hypothesis Deliberation (DHD), a controlled measurement protocol that caches five independently generated messages and replays the same downstream solver, called the integrator, with each message available or hidden. The replay comparison measures a message's trajectory value: whether making the message available helps or harms subsequent reasoning. Across five mathematics and science benchmarks and two openly available model families, gpt-oss-120b and gemma-4-31B-it, wrong-helpful messages appear in every benchmark-model combination. Among wrong-answer messages that change final correctness, more than four in ten changes are helpful in each model. Controlled repeats show that the number of repeatable message effects is unlikely to arise from replay variation alone (p=0.0002). A focused intervention on repeatable wrong-helpful messages finds that the complete message works best, while retaining its reasoning preserves more success than retaining only its answer; the source of the complete-message advantage remains open. Within the same problem, repeated trajectory-value evidence also identifies a better keep-or-remove choice than answer correctness alone. Answer correctness is therefore informative but does not determine trajectory value. DHD measures this missing property and produces reusable labels for learning when agents should listen. △ Less

Submitted 14 August, 2026; originally announced August 2026.

Comments: 24 pages, 9 figures. Includes an appendix and an ancillary reproducibility artifact

Interpreting Language Model Hidden States at Scale

Authors: Jordan Pettyjohn, Mansi Sakarvadia, Nathaniel Hudson, Daniel McKenzie, Kyle Chard, Ian Foster

Abstract: Lens methods interpret large language models (LLMs) by mapping intermediate activations to the output vocabulary, revealing how next-token predictions develop through the network. Trained lenses remain expensive: affine-translator parameters grow quadratically with model width, while exact, full-vocabulary Kullback--Leibler (KL) training dominates memory. Consequently, prior trained lenses have be… ▽ More Lens methods interpret large language models (LLMs) by mapping intermediate activations to the output vocabulary, revealing how next-token predictions develop through the network. Trained lenses remain expensive: affine-translator parameters grow quadratically with model width, while exact, full-vocabulary Kullback--Leibler (KL) training dominates memory. Consequently, prior trained lenses have been applied to models of at most 20B parameters and remain tied to particular component types. We present OmniLens, which applies a single lens family to any model-width activation, whether residual stream, attention, or MLP, and combines two independent scaling techniques. First, low-rank translators make per-lens parameter growth linear in model width and reduce trainable parameters by up to 98.4%. Second, Subset-KL materializes only selected vocabulary logits: its Top-k mode cuts peak training memory by up to 70%, while its importance-sampled variant retains unbiased stochastic gradients for the full KL. These savings enable a dense ensemble of 482 lenses for LLaMA-3.3-70B, providing 6x the coverage of a residual-stream design at the same depth. Model-wide coverage then reveals what single-component lenses cannot: the components where a behavior is most visible need not be those where intervention is most effective, and the most effective interventions lie outside the attention heads examined by prior lens studies. Across three case studies (prompt-injection detection, multi-hop memory injection, and toxicity localization), OmniLens reproduces key published results at substantially lower cost. △ Less

Submitted 10 August, 2026; originally announced August 2026.

Harnessing X-ray Absorption Spectroscopy Data through Multimodal Mining of Battery Literature

Authors: Tanjin He, Aikaterini Vriza, Logan Ward, Xu Huang, Yiming Chen, Anubhav Jain, Gerbrand Ceder, Rajeev S. Assary, Ian T. Foster, Maria K. Y. Chan

Abstract: X-ray absorption spectroscopy (XAS) is central to understanding the local electronic and atomic structure of materials, yet most published spectra remain inaccessible to data-driven analysis because they are embedded in figures and described through fragmented textual context in the literature. Here, we use multimodal (image and text) literature mining to transform this dispersed knowledge into an… ▽ More X-ray absorption spectroscopy (XAS) is central to understanding the local electronic and atomic structure of materials, yet most published spectra remain inaccessible to data-driven analysis because they are embedded in figures and described through fragmented textual context in the literature. Here, we use multimodal (image and text) literature mining to transform this dispersed knowledge into an AI-ready experimental data resource. We developed a scalable spectroscopy data digitization pipeline that identifies XAS figures in full-text articles, digitizes spectral curves, and links each spectrum to accompanying metadata on the measured edge and material. Applying this pipeline to the battery literature produced an open dataset of 13,740 XAS spectra, spanning 66 absorbing elements and diverse battery chemistries, with expert validation confirming accurate extraction of spectral and metadata information. By converting literature-embedded spectra into structured numerical data, this dataset provides a foundation for large-scale XAS analysis, cross-laboratory comparison, high-throughput characterization, and autonomous discovery of advanced materials. △ Less

Submitted 30 July, 2026; v1 submitted 26 July, 2026; originally announced July 2026.

AEGIS: Assay-Aware Protocol Validation and Runtime Monitoring for Open-Source Liquid Handling Robots

Authors: Priyanka V. Setty, Arvind Ramanathan, Ian Foster, Rick Stevens

Abstract: Self-driving laboratories increasingly rely on low-cost liquid handlers such as the Opentrons OT-2, which ship without the pressure-based aspiration monitoring of Hamilton or Tecan systems and are typically run open-loop. Two failure modes go undetected: protocols that are syntactically valid but violate assay-specific invariants (e.g., tip reuse between a PCR template and a no-template control),… ▽ More Self-driving laboratories increasingly rely on low-cost liquid handlers such as the Opentrons OT-2, which ship without the pressure-based aspiration monitoring of Hamilton or Tecan systems and are typically run open-loop. Two failure modes go undetected: protocols that are syntactically valid but violate assay-specific invariants (e.g., tip reuse between a PCR template and a no-template control), and physical execution failures (partial dispense, air bubbles, missing tips) at runtime. We present AEGIS, a two-layer guardian for both. Layer 1 pairs a curated machine-readable assay rule database with an LLM that reasons over OT-2 Python code, reaching an adjusted F1 of 0.97 on a 24-protocol benchmark across five assay families and beating rules-only and LLM-only ablations across five backends; a free open-weight model ties the best proprietary one, so no paid API is required. Layer 2 fits a PCA world model to YOLO-cropped four-frame pipette trajectories; under a leakage-free leave-one-plate-out evaluation it reaches average precision 0.89 and operating-point F1 0.71 (AUROC 0.80), a deployment-faithful number that matches the live demonstration, and we characterize the small-pipette (p20) resolution limit (F1 0.47). A live demonstration on a physical OT-2 (five replicates per condition) catches planted no-tip failures deterministically and partial dispense on coloured dyes, with an always-VLM self-vote gate lifting partial-dispense recall to 5/5; transparent water is a principled limit of any front-view-only monitor, which AEGIS surfaces as low-confidence VLM reasoning rather than a wrong verdict. Cascade triage holds VLM cost near $1.63 per plate versus $10.33 for an always-VLM baseline. AEGIS is open source and, to our knowledge, the first system to unify pre-flight assay-aware validation with runtime visual monitoring for an open-source liquid handler. △ Less

Submitted 17 July, 2026; originally announced July 2026.

Precise but Uncoupled: Reviewer Precision Does Not Guarantee Critique Uptake in Multi-Agent Math Reasoning

Authors: Chih-Hsuan Yang, Jingyan Jiang, Vikram Vasudevan, Cheng-Hau Yang, Huihuo Zheng, Le Chen, Eliu A. Huerta, Venkatram Vishwanath, Ian T. Foster, Rajeev Thakur

Abstract: Many math- and science-oriented agent systems use hierarchical designs with specialized reviewer roles, assuming that a dedicated review stage should help turn wrong candidates into correct ones. We test this assumption on 4,181 verifier-grounded Omni-MATH problems using matched gpt-oss-120b actors. Collaboration adds little on the easiest tiers, but from tier 4 onward the gains open sharply; in t… ▽ More Many math- and science-oriented agent systems use hierarchical designs with specialized reviewer roles, assuming that a dedicated review stage should help turn wrong candidates into correct ones. We test this assumption on 4,181 verifier-grounded Omni-MATH problems using matched gpt-oss-120b actors. Collaboration adds little on the easiest tiers, but from tier 4 onward the gains open sharply; in this harder regime, broadcast-style peer discussion reaches higher final accuracy than a planner-executor-reviewer pipeline (PER). We ask whether this gap is explained by reviewer quality or by whether critique changes the next answer the protocol carries forward. It is not explained by reviewer precision alone: PER's reviewer is more precise than broadcast's (0.861 vs. 0.644), yet evaluator-verified useful critique is much less likely to change the next candidate and produces lower reviewer-guided repair. These results show that reviewer detection quality and critique uptake are empirically separable. Within matched PER interventions, forcing explicit acknowledgment lowers final accuracy, while embedding reviewer guidance directly in the solver's working context partially improves follow-through without closing the gap. Overall, reviewer-centric evaluation can overstate system quality: a protocol may spot errors well yet still fail to solve more problems if it does not act on those critiques. △ Less

Submitted 16 July, 2026; originally announced July 2026.

Comments: 48 pages, 20 figures, 25 tables. Public release website: https://huggingface.co/spaces/AgentsSci/scientific-agent-protocol-traces-site

Toward Trustworthy Autonomous Science: A Two-Year Community Roadmap

Authors: Rafael Ferreira da Silva, Milad Abolhasani, Peter Beaucage, Laura Biven, Michael Bussmann, Kyle Chard, Ryan Coffee, Stephen DeWitt, Sagar Dolas, Carrie Eckert, David Elbert, Ian Foster, Tirthankar Ghosal, Anna Giannakou, Tom Gibbs, Leslie Hamilton, Glenn Lockwood, Theresa Mayer, Ben Mintz, Raffi Nazikian, Sal Nimer, Amanda Randles, Woong Shin, Sreenivas Rangan Sukumar, Frédéric Suter , et al. (3 additional authors not shown)

Abstract: 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 field has since moved faster than anticipated. Multi-agent systems have produced experimentally validated hypotheses, self-driving laboratories have grown more interoperable and orchestrated, reasoning-trained and domain f… ▽ More 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 field has since moved faster than anticipated. Multi-agent systems have produced experimentally validated hypotheses, self-driving laboratories have grown more interoperable and orchestrated, reasoning-trained and domain foundation models have raised the capability ceiling, and the Genesis Mission has placed autonomous experimentation at the center of U.S. federal science strategy, with industry emerging as a primary actor. Progress has met a sobering counter-current, including a corrected flagship discovery result, benchmarks showing that agents which rival experts on closed-ended questions still complete only a fraction of open-ended research, and fabricated citations surfacing at leading venues. We read this as the defining tension of the field. Producing a candidate discovery is no longer the hard part, but verifying it is, and this asymmetry now limits autonomous science more than raw model capability. We update the roadmap around seven dimensions, revisiting the original five and elevating two former cross-cutting concerns, trust, verification, and reproducibility, and safety, security, and governance, to first-class status. We assess the original milestones (M1 through M14) as achieved, partially achieved, reframed, or open, add four new milestones (M15 through M18), and scope the path forward to a two-year horizon. The first year concentrates on interfaces, protocol adoption, and the scaffolding of verification, and the second targets federation, zero-trust coordination, and governance. Throughout, we position the grassroots network as the interoperability fabric that lets national programs, international initiatives, and commercial platforms connect rather than re-silo. △ Less

Submitted 13 July, 2026; originally announced July 2026.

Report number: ORNL/TM-2026/4663

Towards Transparent Checkpointing with AI-driven Code Generation

Authors: Hai Duc Nguyen, Tekin Bicer, Kyle Chard, Ian Foster, Bogdan Nicolae

Abstract: 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. We ask whether a frontier large language model can perform this work end-to-end without human intervention. We assemble a benchmark suite of MPI applications spanning diverse domains and computation patterns, and drive an… ▽ More 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. We ask whether a frontier large language model can perform this work end-to-end without human intervention. We assemble a benchmark suite of MPI applications spanning diverse domains and computation patterns, and drive an iterative code-generation loop for each application using Anthropic's Claude Opus 4.7 invoked through the OpenCode CLI. Across six scientific applications, the LLM generates working checkpoint/restart code in 50 minutes on average while consuming 3.4 M tokens per application. The generated code adds negligible overhead during normal failure-free execution on five of six applications and recovers from injected process failures with efficiency comparable to human-engineered checkpoint/restart implementations. These results suggest that automated end-to-end LLM-driven resilience engineering is technically viable today for a meaningful fraction of HPC applications. △ Less

Submitted 29 June, 2026; originally announced June 2026.

ACM Class: D.4.5; I.2.2; D.1.3; I.2.7

Journal ref: FlexScience'26: The 2026 Workshop on AI and Scientific Computing at Scale using Flexible Computing Infrastructures (in conjunction with HPDC'26)

StreamGuard: Low-Overhead Resilience for Real-time HPC Data Streams

Authors: Hai Duc Nguyen, Bogdan Nicolae, Tekin Bicer, Amal Gueroudji, Matthieu Dorier, Kyle Chard, Ian Foster

Abstract: Real-time scientific workflows operate on continuous data streams and must produce timely, high-quality results despite executing on complex, failure-prone infrastructure. Hardware faults, network disruptions, and performance anomalies caused by resource contention or system heterogeneity can severely degrade performance and violate real-time constraints. We focus on strengthening the resilience o… ▽ More Real-time scientific workflows operate on continuous data streams and must produce timely, high-quality results despite executing on complex, failure-prone infrastructure. Hardware faults, network disruptions, and performance anomalies caused by resource contention or system heterogeneity can severely degrade performance and violate real-time constraints. We focus on strengthening the resilience of the producer-consumer streaming pattern, a fundamental building block of scientific streaming workflows. We present two complementary techniques: (i) a dynamic, asynchronous, non-blocking checkpointing mechanism that preserves progress without interrupting computation, and (ii) a progress-aware load redistribution strategy that detects slow workers and proactively rebalances tasks. Together, these mechanisms maintain forward progress and balanced execution even in highly error-prone environments. Experimental results show that our approach reduces the impact of failures and performance anomalies by up to 6x, while introducing less than 1% overhead in failure-free execution. △ Less

Submitted 29 June, 2026; originally announced June 2026.

ACM Class: D.4.5; C.4; C.2.4

Journal ref: ICS'26: The 2026 ACM International Conference on Supercomputing

When More Cores Hurts: The Vector Database Scaling Paradox in HPC

Authors: Seth Ockerman, Song Young Oh, Amal Gueroudji, Rochana Chaturvedi, Philip Carns, Nicholas Chia, Matthieu Dorier, Robert Latham, Tanwi Mallick, Swan Perarnau, Robert Underwood, Kyle Chard, Ian Foster, Robert Ross, Shivaram Venkataraman

Abstract: Vector databases have been designed and optimized for cloud environments; however, emerging scientific AI workloads (e.g., molecular search, meteorological trajectory detection, and literature-driven hypothesis generation) demand efficient, scalable execution on HPC systems. We present a large-scale evaluation of three state-of-the-art vector databases -- Qdrant, Milvus, and Weaviate -- on two pro… ▽ More Vector databases have been designed and optimized for cloud environments; however, emerging scientific AI workloads (e.g., molecular search, meteorological trajectory detection, and literature-driven hypothesis generation) demand efficient, scalable execution on HPC systems. We present a large-scale evaluation of three state-of-the-art vector databases -- Qdrant, Milvus, and Weaviate -- on two production supercomputers, scaling to 256 distributed workers across 64 compute nodes. We evaluate representative workload patterns -- mixed read/write and write-then-read -- using popular benchmarks, multimodal embeddings, and a novel real-world scientific dataset. Our results reveal that workload characteristics can limit latency reduction, additional cores can reduce query throughput by up to 30.67%, and scaling from 16 to 256 workers (16x) only yields a 5.46x improvement. This scaling paradox exposes the fundamental mismatch between cloud-oriented designs and HPC systems, highlighting the need for new, HPC-aware vector database designs. △ Less

Submitted 7 June, 2026; originally announced June 2026.

From Knowledge to Action: Outcomes of the 2025 Large Language Model (LLM) Hackathon for Applications in Materials Science and Chemistry

Authors: Aritra Roy, Kevin Shen, Andrew MacBride, Awwal Oladipupo, Mudassra Taskeen, Wojtek Treyde, Ruaa A. E. A. Abakar, Ahmad D. Abbas, Elsayed Abdelfatah, Abbas A. Abdullahi, Seham S. Abyah, Chahd Rahyl Adjmi, Fariha Agbere, Savyasanchi Aggarwal, Muhammad Ahmed, Tasnim Ahmed, Motasem Ajlouni, Mattias Akke, Hussein AlAdwan, Anwaar S. Alazani, Zahra A. Alharbi, Wajd A. Aljulyhi, Mohammed A. AlKubaish, Fatima A. Almahri, Sayed A. Almohri , et al. (328 additional authors not shown)

Abstract: Large language models (LLMs) are rapidly changing how researchers in materials science and chemistry discover, organize, and act on scientific knowledge. This paper analyzes a broad set of community-developed LLM applications in an effort to identify emerging patterns in how these systems can be used across the scientific research lifecycle. We organize the projects into two complementary categori… ▽ More Large language models (LLMs) are rapidly changing how researchers in materials science and chemistry discover, organize, and act on scientific knowledge. This paper analyzes a broad set of community-developed LLM applications in an effort to identify emerging patterns in how these systems can be used across the scientific research lifecycle. We organize the projects into two complementary categories: Knowledge Infrastructure, systems that structure, retrieve, synthesize, and validate scientific information; and Action Systems, systems that execute, coordinate, or automate scientific work across computational and experimental environments. The submissions reveal a shift from single-purpose LLM tools toward integrated, multi-agent workflows that combine retrieval, reasoning, tool use, and domain-specific validation. Prominent themes include retrieval-augmented generation as grounding infrastructure, persistent structured knowledge representations, multimodal and multilingual scientific inputs, and early progress toward laboratory-integrated closed-loop systems. Together, these results suggest that LLMs are evolving from general-purpose assistants into composable infrastructure for scientific reasoning and action. This work provides a community snapshot of that transition and a practical taxonomy for understanding emerging LLM-enabled workflows in materials science and chemistry. △ Less

Submitted 4 May, 2026; originally announced May 2026.

Comments: This paper reflects contributions from hundreds of researchers worldwide through an event, follow-on discussions, and project development exploring LLM applications in materials science and chemistry. While unconventional, it captures a timely, broad, and efficient community exploration of a rapidly evolving field and offers value to the arXiv community

Icicle: Scalable Metadata Indexing and Real-Time Monitoring for HPC File Systems

Authors: Haochen Pan, Ryan Chard, Song Young Oh, Maxime Gonthier, Valérie Hayot-Sasson, Geoffrey Lentner, Joe Bottigliero, Rachana Ananthakrishnan, Kyle Chard, Ian Foster

Abstract: 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 utilities such as find and du fail to scale to these sizes. While external indexing tools like GUFI and Brindexer improve query performance, they remain batch-oriented and unsuitable for heterogeneous, rapidly evolving env… ▽ More 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 utilities such as find and du fail to scale to these sizes. While external indexing tools like GUFI and Brindexer improve query performance, they remain batch-oriented and unsuitable for heterogeneous, rapidly evolving environments. We present Icicle, a scalable framework for continuous file system metadata indexing and monitoring. Icicle maintains a unified, up-to-date, and queryable view of file system state while supporting both periodic snapshot-based ingestion for bulk metadata updates and event-based ingestion for real-time synchronization from production systems such as Lustre and IBM Storage Scale. Built on Apache Kafka and Apache Flink, Icicle provides high-throughput, fault-tolerant, and horizontally scalable ingestion of metadata events into two complementary search indexes, enabling both individual file discovery and aggregate summary statistics by user, group, and directory. This architecture enables efficient support for both coarse-grained administrative queries and interactive analytics over billions of objects. Our experimental evaluation on production-scale HPC datasets demonstrates order-of-magnitude throughput improvements over existing monitoring and indexing approaches, with tunable options for balancing consistency, latency, and metadata freshness. △ Less

Submitted 11 April, 2026; originally announced April 2026.

Comments: ISC High Performance 2026 research paper, camera-ready

BioAlchemy: Distilling Biological Literature into Reasoning-Ready Reinforcement Learning Training Data

Authors: Brian Hsu, Ozan Gökdemir, Carlo Siebenschuh, Bruce Parrello, Neil Getty, Thomas S. Brettin, Rick L. Stevens, Ian T. Foster, Nicholas Chia, Arvind Ramanathan

Abstract: Despite the large corpus of biology training text, the impact of reasoning models on biological research generally lags behind math and coding. In this work, we show that biology questions from current large-scale reasoning datasets do not align well with modern research topic distributions in biology, and that this topic imbalance may negatively affect performance. In addition, we find that metho… ▽ More Despite the large corpus of biology training text, the impact of reasoning models on biological research generally lags behind math and coding. In this work, we show that biology questions from current large-scale reasoning datasets do not align well with modern research topic distributions in biology, and that this topic imbalance may negatively affect performance. In addition, we find that methods for extracting challenging and verifiable research problems from biology research text are a critical yet underdeveloped ingredient in applying reinforcement learning for better performance on biology research tasks. We introduce BioAlchemy, a pipeline for sourcing a diverse set of verifiable question-and-answer pairs from a scientific corpus of biology research text. We curate BioAlchemy-345K, a training dataset containing over 345K scientific reasoning problems in biology. Then, we demonstrate how aligning our dataset to the topic distribution of modern scientific biology can be used with reinforcement learning to improve reasoning performance. Finally, we present BioAlchemist-8B, which improves over its base reasoning model by 9.12% on biology benchmarks. These results demonstrate the efficacy of our approach for developing stronger scientific reasoning capabilities in biology. The BioAlchemist-8B model is available at: https://huggingface.co/BioAlchemy. △ Less

Submitted 3 April, 2026; originally announced April 2026.

ACM Class: I.2.6; I.2.7; J.3

Scalable Cross-Facility Federated Learning for Scientific Foundation Models on Multiple Supercomputers

Authors: Yijiang Li, Zilinghan Li, Kyle Chard, Ian Foster, Todd Munson, Ravi Madduri, Kibaek Kim

Abstract: Artificial Intelligence for scientific applications increasingly requires training large models on data that cannot be centralized due to privacy constraints, data sovereignty, or the sheer volume of data generated. Federated learning (FL) addresses this by enabling collaborative training without centralizing raw data, but scientific applications demand model scales that requires extensive computi… ▽ More Artificial Intelligence for scientific applications increasingly requires training large models on data that cannot be centralized due to privacy constraints, data sovereignty, or the sheer volume of data generated. Federated learning (FL) addresses this by enabling collaborative training without centralizing raw data, but scientific applications demand model scales that requires extensive computing resources, typically offered at High Performance Computing (HPC) facilities. Deploying FL experiments across HPC facilities introduces challenges beyond cloud or enterprise settings. We present a comprehensive cross-facility FL framework for heterogeneous HPC environments, built on Advanced Privacy-Preserving Federated Learning (APPFL) framework with Globus Compute and Transfer orchestration, and evaluate it across four U.S. Department of Energy (DOE) leadership-class supercomputers. We demonstrate that FL experiments across HPC facilities are practically achievable, characterize key sources of heterogeneity impacting the training performance, and show that algorithmic choices matter significantly under realistic HPC scheduling conditions. We validate the scientific applicability by fine-tuning a large language model on a chemistry instruction dataset, and identify scheduler-aware algorithm design as a critical open challenge for future deployments. △ Less

Submitted 19 March, 2026; originally announced March 2026.

PRISM: Protocol Refinement through Intelligent Simulation Modeling

Authors: Brian Hsu, Priyanka V Setty, Rory M Butler, Ryan Lewis, Casey Stone, Rebecca Weinberg, Thomas Brettin, Rick Stevens, Ian Foster, Arvind Ramanathan

Abstract: Automating experimental protocol design and execution remains as a fundamental bottleneck in realizing self-driving laboratories. We introduce PRISM (Protocol Refinement through Intelligent Simulation Modeling), a framework that automates the design, validation, and execution of experimental protocols on a laboratory platform composed of off-the-shelf robotic instruments. PRISM uses a set of langu… ▽ More Automating experimental protocol design and execution remains as a fundamental bottleneck in realizing self-driving laboratories. We introduce PRISM (Protocol Refinement through Intelligent Simulation Modeling), a framework that automates the design, validation, and execution of experimental protocols on a laboratory platform composed of off-the-shelf robotic instruments. PRISM uses a set of language-model-based agents that work together to generate and refine experimental steps. The process begins with automatically gathering relevant procedures from web-based sources describing experimental workflows. These are converted into structured experimental steps (e.g., liquid handling steps, deck layout and other related operations) through a planning, critique, and validation loop. The finalized steps are translated into the Argonne MADSci protocol format, which provides a unified interface for coordinating multiple robotic instruments (Opentrons OT-2 liquid handler, PF400 arm, Azenta plate sealer and peeler) without requiring human intervention between steps. To evaluate protocol-generation performance, we benchmarked both single reasoning models and multi-agent workflow across constrained and open-ended prompting paradigms. The resulting protocols were validated in a digital-twin environment built in NVIDIA Omniverse to detect physical or sequencing errors before execution. Using Luna qPCR amplification and Cell Painting as case studies, we demonstrate PRISM as a practical end-to-end workflow that bridges language-based protocol generation, simulation-based validation, and automated robotic execution. △ Less

Submitted 8 January, 2026; originally announced January 2026.

Comments: 43 pages, 8 figures, submitted to RSC Digital Discovery. Equal contribution: B. Hsu, P.V. Setty, R.M. Butler. Corresponding author: A. Ramanathan

Scalable Agentic Reasoning for Designing Biologics Targeting Intrinsically Disordered Proteins

Authors: Matthew Sinclair, Moeen Meigooni, Archit Vasan, Ozan Gokdemir, Xinran Lian, Heng Ma, Yadu Babuji, Alexander Brace, Khalid Hossain, Carlo Siebenschuh, Thomas Brettin, Kyle Chard, Christopher Henry, Venkatram Vishwanath, Rick L. Stevens, Ian T. Foster, Arvind Ramanathan

Abstract: Intrinsically disordered proteins (IDPs) represent crucial therapeutic targets due to their significant role in disease -- approximately 80\% of cancer-related proteins contain long disordered regions -- but their lack of stable secondary/tertiary structures makes them "undruggable". While recent computational advances, such as diffusion models, can design high-affinity IDP binders, translating th… ▽ More Intrinsically disordered proteins (IDPs) represent crucial therapeutic targets due to their significant role in disease -- approximately 80\% of cancer-related proteins contain long disordered regions -- but their lack of stable secondary/tertiary structures makes them "undruggable". While recent computational advances, such as diffusion models, can design high-affinity IDP binders, translating these to practical drug discovery requires autonomous systems capable of reasoning across complex conformational ensembles and orchestrating diverse computational tools at scale.To address this challenge, we designed and implemented StructBioReasoner, a scalable multi-agent system for designing biologics that can be used to target IDPs. StructBioReasoner employs a novel tournament-based reasoning framework where specialized agents compete to generate and refine therapeutic hypotheses, naturally distributing computational load for efficient exploration of the vast design space. Agents integrate domain knowledge with access to literature synthesis, AI-structure prediction, molecular simulations, and stability analysis, coordinating their execution on HPC infrastructure via an extensible federated agentic middleware, Academy. We benchmark StructBioReasoner across Der f 21 and NMNAT-2 and demonstrate that over 50\% of 787 designed and validated candidates for Der f 21 outperformed the human-designed reference binders from literature, in terms of improved binding free energy. For the more challenging NMNAT-2 protein, we identified three binding modes from 97,066 binders, including the well-studied NMNAT2:p53 interface. Thus, StructBioReasoner lays the groundwork for agentic reasoning systems for IDP therapeutic discovery on Exascale platforms. △ Less

Submitted 27 April, 2026; v1 submitted 17 December, 2025; originally announced December 2025.

Comments: This manuscript is in press at the upcoming Proceedings of the Platform for Advanced Scientific Computing (PASC) 26 Conference

Who Gets the Reward & Who Gets the Blame? Evaluation-Aligned Training Signals for Multi-LLM Agents

Authors: Chih-Hsuan, Yang, Tanwi Mallick, Le Chen, Krishnan Raghavan, Amal Gueroudji, Ian T. Foster, Rajeev Thakur

Abstract: Large Language Models (LLMs) in multi-agent systems (MAS) have shown promise for complex tasks, yet current training methods lack principled ways to connect system-level evaluation with agent- and message-level learning. We propose a theoretical framework that unifies cooperative game-theoretic attribution with process reward modeling to transform system evaluation to agent credit to response-leve… ▽ More Large Language Models (LLMs) in multi-agent systems (MAS) have shown promise for complex tasks, yet current training methods lack principled ways to connect system-level evaluation with agent- and message-level learning. We propose a theoretical framework that unifies cooperative game-theoretic attribution with process reward modeling to transform system evaluation to agent credit to response-level signals. Unlike prior approaches that rely only on attribution (Shapley) or step-level labels (PRM), our method produces local, signed, and credit-conserving signals. In success cases, Shapley-based credit assignment fairly allocates outcomes across agents and is refined into per-message rewards that promote cooperation while discouraging redundancy or sabotage; in failure cases, first-error localization yields repair-aware preferences that penalize harmful steps while rewarding corrective attempts. The resulting signals are bounded, cooperative, and directly compatible with reinforcement- or preference-based post-training, providing a unified and auditable pathway from global evaluation to local supervision in LLM multi-agent training. Our contribution is conceptual: we present a theoretical foundation and training signals, leaving empirical validation for future work. △ Less

Submitted 1 July, 2026; v1 submitted 11 November, 2025; originally announced November 2025.

Comments: Accepted at the NeurIPS 2025 Workshop on Bridging Language, Agent, and World Models for Reasoning and Planning (LAW 2025)

OmniCast: A Masked Latent Diffusion Model for Weather Forecasting Across Time Scales

Authors: Tung Nguyen, Tuan Pham, Troy Arcomano, Veerabhadra Kotamarthi, Ian Foster, Sandeep Madireddy, Aditya Grover

Abstract: Accurate weather forecasting across time scales is critical for anticipating and mitigating the impacts of climate change. Recent data-driven methods based on deep learning have achieved significant success in the medium range, but struggle at longer subseasonal-to-seasonal (S2S) horizons due to error accumulation in their autoregressive approach. In this work, we propose OmniCast, a scalable and… ▽ More Accurate weather forecasting across time scales is critical for anticipating and mitigating the impacts of climate change. Recent data-driven methods based on deep learning have achieved significant success in the medium range, but struggle at longer subseasonal-to-seasonal (S2S) horizons due to error accumulation in their autoregressive approach. In this work, we propose OmniCast, a scalable and skillful probabilistic model that unifies weather forecasting across timescales. OmniCast consists of two components: a VAE model that encodes raw weather data into a continuous, lower-dimensional latent space, and a diffusion-based transformer model that generates a sequence of future latent tokens given the initial conditioning tokens. During training, we mask random future tokens and train the transformer to estimate their distribution given conditioning and visible tokens using a per-token diffusion head. During inference, the transformer generates the full sequence of future tokens by iteratively unmasking random subsets of tokens. This joint sampling across space and time mitigates compounding errors from autoregressive approaches. The low-dimensional latent space enables modeling long sequences of future latent states, allowing the transformer to learn weather dynamics beyond initial conditions. OmniCast performs competitively with leading probabilistic methods at the medium-range timescale while being 10x to 20x faster, and achieves state-of-the-art performance at the subseasonal-to-seasonal scale across accuracy, physics-based, and probabilistic metrics. Furthermore, we demonstrate that OmniCast can generate stable rollouts up to 100 years ahead. Code and model checkpoints are available at https://github.com/tung-nd/omnicast. △ Less

Submitted 20 October, 2025; originally announced October 2025.

Comments: Neural Information Processing Systems (NeurIPS 2025)

FIRST: Federated Inference Resource Scheduling Toolkit for Scientific AI Model Access

Authors: Aditya Tanikanti, Benoit Côté, Yanfei Guo, Le Chen, Nickolaus Saint, Ryan Chard, Ken Raffenetti, Rajeev Thakur, Thomas Uram, Ian Foster, Michael E. Papka, Venkatram Vishwanath

Abstract: We present the Federated Inference Resource Scheduling Toolkit (FIRST), a framework enabling Inference-as-a-Service across distributed High-Performance Computing (HPC) clusters. FIRST provides cloud-like access to diverse AI models, like Large Language Models (LLMs), on existing HPC infrastructure. Leveraging Globus Auth and Globus Compute, the system allows researchers to run parallel inference w… ▽ More We present the Federated Inference Resource Scheduling Toolkit (FIRST), a framework enabling Inference-as-a-Service across distributed High-Performance Computing (HPC) clusters. FIRST provides cloud-like access to diverse AI models, like Large Language Models (LLMs), on existing HPC infrastructure. Leveraging Globus Auth and Globus Compute, the system allows researchers to run parallel inference workloads via an OpenAI-compliant API on private, secure environments. This cluster-agnostic API allows requests to be distributed across federated clusters, targeting numerous hosted models. FIRST supports multiple inference backends (e.g., vLLM), auto-scales resources, maintains "hot" nodes for low-latency execution, and offers both high-throughput batch and interactive modes. The framework addresses the growing demand for private, secure, and scalable AI inference in scientific workflows, allowing researchers to generate billions of tokens daily on-premises without relying on commercial cloud infrastructure. △ Less

Submitted 15 October, 2025; originally announced October 2025.

Journal ref: SC Workshops '25, Proceedings of the SC '25 Workshops of the International Conference for High Performance Computing, Networking, Storage and Analysis, ACM, pp. 52-60, 2025

Agentic Discovery: Closing the Loop with Cooperative Agents

Authors: J. Gregory Pauloski, Kyle Chard, Ian T. Foster

Abstract: As data-driven methods, artificial intelligence (AI), and automated workflows accelerate scientific tasks, we see the rate of discovery increasingly limited by human decision-making tasks such as setting objectives, generating hypotheses, and designing experiments. We postulate that cooperative agents are needed to augment the role of humans and enable autonomous discovery. Realizing such agents w… ▽ More As data-driven methods, artificial intelligence (AI), and automated workflows accelerate scientific tasks, we see the rate of discovery increasingly limited by human decision-making tasks such as setting objectives, generating hypotheses, and designing experiments. We postulate that cooperative agents are needed to augment the role of humans and enable autonomous discovery. Realizing such agents will require progress in both AI and infrastructure. △ Less

Submitted 14 October, 2025; originally announced October 2025.

Comments: Published in IEEE Computer Volume 58 Issue 10

The False Promise of Zero-Shot Super-Resolution in Machine-Learned Operators

Authors: Mansi Sakarvadia, Kareem Hegazy, Amin Totounferoush, Kyle Chard, Yaoqing Yang, Ian Foster, Michael W. Mahoney

Abstract: A core challenge in scientific machine learning, and scientific computing more generally, is modeling continuous phenomena which (in practice) are represented discretely. Machine-learned operators (MLOs) have been introduced as a means to achieve this modeling goal, as this class of architecture can perform inference at arbitrary resolution. In this work, we evaluate whether this architectural inn… ▽ More A core challenge in scientific machine learning, and scientific computing more generally, is modeling continuous phenomena which (in practice) are represented discretely. Machine-learned operators (MLOs) have been introduced as a means to achieve this modeling goal, as this class of architecture can perform inference at arbitrary resolution. In this work, we evaluate whether this architectural innovation is sufficient to perform "zero-shot super-resolution," namely to enable a model to serve inference on higher-resolution data than that on which it was originally trained. We comprehensively evaluate both zero-shot sub-resolution and super-resolution (i.e., multi-resolution) inference in MLOs. We decouple multi-resolution inference into two key behaviors: 1) extrapolation to varying frequency information; and 2) interpolating across varying resolutions. We empirically demonstrate that MLOs fail to do both of these tasks in a zero-shot manner. Consequently, we find MLOs are not able to perform accurate inference at resolutions different from those on which they were trained, and instead they are brittle and susceptible to aliasing. To address these failure modes, we propose a simple, computationally-efficient, and data-driven multi-resolution training protocol that overcomes aliasing and that provides robust multi-resolution generalization. △ Less

Submitted 26 February, 2026; v1 submitted 8 October, 2025; originally announced October 2025.

Comments: Published in the Proceedings of the International Conference on Learning Representations (ICLR), 2026

Steering an Active Learning Workflow Towards Novel Materials Discovery via Queue Prioritization

Authors: Marcus Schwarting, Logan Ward, Nathaniel Hudson, Xiaoli Yan, Ben Blaiszik, Santanu Chaudhuri, Eliu Huerta, Ian Foster

Abstract: Generative AI poses both opportunities and risks for solving inverse design problems in the sciences. Generative tools provide the ability to expand and refine a search space autonomously, but do so at the cost of exploring low-quality regions until sufficiently fine tuned. Here, we propose a queue prioritization algorithm that combines generative modeling and active learning in the context of a d… ▽ More Generative AI poses both opportunities and risks for solving inverse design problems in the sciences. Generative tools provide the ability to expand and refine a search space autonomously, but do so at the cost of exploring low-quality regions until sufficiently fine tuned. Here, we propose a queue prioritization algorithm that combines generative modeling and active learning in the context of a distributed workflow for exploring complex design spaces. We find that incorporating an active learning model to prioritize top design candidates can prevent a generative AI workflow from expending resources on nonsensical candidates and halt potential generative model decay. For an existing generative AI workflow for discovering novel molecular structure candidates for carbon capture, our active learning approach significantly increases the number of high-quality candidates identified by the generative model. We find that, out of 1000 novel candidates, our workflow without active learning can generate an average of 281 high-performing candidates, while our proposed prioritization with active learning can generate an average 604 high-performing candidates. △ Less

Submitted 29 September, 2025; originally announced September 2025.

To Stream or Not to Stream: Towards A Quantitative Model for Remote HPC Processing Decisions

Authors: Flavio Castro, Weijian Zheng, Joaquin Chung, Ian Foster, Rajkumar Kettimuthu

Abstract: Modern scientific instruments generate data at rates that increasingly exceed local compute capabilities and, when paired with the staging and I/O overheads of file-based transfers, also render file-based use of remote HPC resources impractical for time-sensitive analysis and experimental steering. Real-time streaming frameworks promise to reduce latency and improve system efficiency, but lack a p… ▽ More Modern scientific instruments generate data at rates that increasingly exceed local compute capabilities and, when paired with the staging and I/O overheads of file-based transfers, also render file-based use of remote HPC resources impractical for time-sensitive analysis and experimental steering. Real-time streaming frameworks promise to reduce latency and improve system efficiency, but lack a principled way to assess their feasibility. In this work, we introduce a quantitative framework and an accompanying Streaming Speed Score to evaluate whether remote high-performance computing (HPC) resources can provide timely data processing compared to local alternatives. Our model incorporates key parameters including data generation rate, transfer efficiency, remote processing power, and file input/output overhead to compute total processing completion time and identify operational regimes where streaming is beneficial. We motivate our methodology with use cases from facilities such as APS, FRIB, LCLS-II, and the LHC, and validate our approach through an illustrative case study based on LCLS-II data. Our measurements show that streaming can achieve up to 97% lower end-to-end completion time than file-based methods under high data rates, while worst-case congestion can increase transfer times by over an order of magnitude, underscoring the importance of tail latency in streaming feasibility decisions. △ Less

Submitted 29 September, 2025; v1 submitted 23 September, 2025; originally announced September 2025.

XaaS Containers: Performance-Portable Representation With Source and IR Containers

Authors: Marcin Copik, Eiman Alnuaimi, Alok Kamatar, Valerie Hayot-Sasson, Alberto Madonna, Todd Gamblin, Kyle Chard, Ian Foster, Torsten Hoefler

Abstract: High-performance computing (HPC) systems and cloud data centers are converging, and containers are becoming the default method of portable software deployment. Yet, while containers simplify software management, they face significant performance challenges in HPC environments as they must sacrifice hardware-specific optimizations to achieve portability. Although HPC containers can use runtime hook… ▽ More High-performance computing (HPC) systems and cloud data centers are converging, and containers are becoming the default method of portable software deployment. Yet, while containers simplify software management, they face significant performance challenges in HPC environments as they must sacrifice hardware-specific optimizations to achieve portability. Although HPC containers can use runtime hooks to access optimized MPI libraries and GPU devices, they are limited by application binary interface (ABI) compatibility and cannot overcome the effects of early-stage compilation decisions. Acceleration as a Service (XaaS) proposes a vision of performance-portable containers, where a containerized application should achieve peak performance across all HPC systems. We present a practical realization of this vision through Source and Intermediate Representation (IR) containers, where we delay performance-critical decisions until the target system specification is known. We analyze specialization mechanisms in HPC software and propose a new LLM-assisted method for automatic discovery of specializations. By examining the compilation pipeline, we develop a methodology to build containers optimized for target architectures at deployment time. Our prototype demonstrates that new XaaS containers combine the convenience of containerization with the performance benefits of system-specialized builds. △ Less

Submitted 22 September, 2025; originally announced September 2025.

Comments: Accepted at the International Conference for High Performance Computing, Networking, Storage and Analysis (SC'25)

FragmentGPT: A Unified GPT Model for Fragment Growing, Linking, and Merging in Molecular Design

Authors: Xuefeng Liu, Songhao Jiang, Qinan Huang, Tinson Xu, Ian Foster, Mengdi Wang, Hening Lin, Rick Stevens

Abstract: Fragment-Based Drug Discovery (FBDD) is a popular approach in early drug development, but designing effective linkers to combine disconnected molecular fragments into chemically and pharmacologically viable candidates remains challenging. Further complexity arises when fragments contain structural redundancies, like duplicate rings, which cannot be addressed by simply adding or removing atoms or b… ▽ More Fragment-Based Drug Discovery (FBDD) is a popular approach in early drug development, but designing effective linkers to combine disconnected molecular fragments into chemically and pharmacologically viable candidates remains challenging. Further complexity arises when fragments contain structural redundancies, like duplicate rings, which cannot be addressed by simply adding or removing atoms or bonds. To address these challenges in a unified framework, we introduce FragmentGPT, which integrates two core components: (1) a novel chemically-aware, energy-based bond cleavage pre-training strategy that equips the GPT-based model with fragment growing, linking, and merging capabilities, and (2) a novel Reward Ranked Alignment with Expert Exploration (RAE) algorithm that combines expert imitation learning for diversity enhancement, data selection and augmentation for Pareto and composite score optimality, and Supervised Fine-Tuning (SFT) to align the learner policy with multi-objective goals. Conditioned on fragment pairs, FragmentGPT generates linkers that connect diverse molecular subunits while simultaneously optimizing for multiple pharmaceutical goals. It also learns to resolve structural redundancies-such as duplicated fragments-through intelligent merging, enabling the synthesis of optimized molecules. FragmentGPT facilitates controlled, goal-driven molecular assembly. Experiments and ablation studies on real-world cancer datasets demonstrate its ability to generate chemically valid, high-quality molecules tailored for downstream drug discovery tasks. △ Less

Submitted 23 September, 2025; v1 submitted 13 September, 2025; originally announced September 2025.

Automated MCQA Benchmarking at Scale: Evaluating Reasoning Traces as Retrieval Sources for Domain Adaptation of Small Language Models

Authors: Ozan Gokdemir, Neil Getty, Robert Underwood, Sandeep Madireddy, Franck Cappello, Arvind Ramanathan, Ian T. Foster, Rick L. Stevens

Abstract: As scientific knowledge grows at an unprecedented pace, evaluation benchmarks must evolve to reflect new discoveries and ensure language models are tested on current, diverse literature. We propose a scalable, modular framework for generating multiple-choice question-answering (MCQA) benchmarks directly from large corpora of scientific papers. Our pipeline automates every stage of MCQA creation, i… ▽ More As scientific knowledge grows at an unprecedented pace, evaluation benchmarks must evolve to reflect new discoveries and ensure language models are tested on current, diverse literature. We propose a scalable, modular framework for generating multiple-choice question-answering (MCQA) benchmarks directly from large corpora of scientific papers. Our pipeline automates every stage of MCQA creation, including PDF parsing, semantic chunking, question generation, and model evaluation. As a case study, we generate more than 16,000 MCQs from 22,000 open-access articles in radiation and cancer biology. We then evaluate a suite of small language models (1.1B-14B parameters) on these questions, comparing baseline accuracy with retrieval-augmented generation (RAG) from paper-derived semantic chunks and from reasoning traces distilled from GPT-4.1. We find that reasoning-trace retrieval consistently improves performance on both synthetic and expert-annotated benchmarks, enabling several small models to surpass GPT-4 on the 2023 Astro Radiation and Cancer Biology exam. △ Less

Submitted 12 September, 2025; originally announced September 2025.

Comments: This manuscript has been accepted for publication at the Supercomputing 25 (SC '25) Conference (Frontiers in Generative AI for HPC Science and Engineering: Foundations, Challenges, and Opportunities Workshop) in St. Louis, MO, USA on November 16th, 2025. It will appear in the SC25 Workshop Proceedings after that date

ACM Class: I.2.7; I.2.11

Addressing Reproducibility Challenges in HPC with Continuous Integration

Authors: Valérie Hayot-Sasson, Nathaniel Hudson, André Bauer, Maxime Gonthier, Ian Foster, Kyle Chard

Abstract: The high-performance computing (HPC) community has adopted incentive structures to motivate reproducible research, with major conferences awarding badges to papers that meet reproducibility requirements. Yet, many papers do not meet such requirements. The uniqueness of HPC infrastructure and software, coupled with strict access requirements, may limit opportunities for reproducibility. In the abse… ▽ More The high-performance computing (HPC) community has adopted incentive structures to motivate reproducible research, with major conferences awarding badges to papers that meet reproducibility requirements. Yet, many papers do not meet such requirements. The uniqueness of HPC infrastructure and software, coupled with strict access requirements, may limit opportunities for reproducibility. In the absence of resource access, we believe that regular documented testing, through continuous integration (CI), coupled with complete provenance information, can be used as a substitute. Here, we argue that better HPC-compliant CI solutions will improve reproducibility of applications. We present a survey of reproducibility initiatives and describe the barriers to reproducibility in HPC. To address existing limitations, we present a GitHub Action, CORRECT, that enables secure execution of tests on remote HPC resources. We evaluate CORRECT's usability across three different types of HPC applications, demonstrating the effectiveness of using CORRECT for automating and documenting reproducibility evaluations. △ Less

Submitted 28 August, 2025; originally announced August 2025.

Experiences with Model Context Protocol Servers for Science and High Performance Computing

Authors: Haochen Pan, Ryan Chard, Reid Mello, Christopher Grams, Tanjin He, Alexander Brace, Owen Price Skelly, Will Engler, Hayden Holbrook, Song Young Oh, Maxime Gonthier, Michael Papka, Ben Blaiszik, Kyle Chard, Ian Foster

Abstract: Large language model (LLM)-powered agents are increasingly used to plan and execute scientific workflows, yet most research cyberinfrastructure (CI) exposes heterogeneous APIs and implements security models that present barriers for use by agents. We report on our experience using the Model Context Protocol (MCP) as a unifying interface that makes research capabilities discoverable, invokable, and… ▽ More Large language model (LLM)-powered agents are increasingly used to plan and execute scientific workflows, yet most research cyberinfrastructure (CI) exposes heterogeneous APIs and implements security models that present barriers for use by agents. We report on our experience using the Model Context Protocol (MCP) as a unifying interface that makes research capabilities discoverable, invokable, and composable. Our approach is pragmatic: we implement thin MCP servers over mature services, including Globus Transfer, Compute, and Search; status APIs exposed by computing facilities; Octopus event fabric; and domain-specific tools such as Garden and Galaxy. We use case studies in computational chemistry, bioinformatics, quantum chemistry, and filesystem monitoring to illustrate how this MCP-oriented architecture can be used in practice. We distill lessons learned and outline open challenges in evaluation and trust for agent-led science. △ Less

Submitted 25 August, 2025; originally announced August 2025.

Comments: 11 pages, including a 4-page appendix

Understanding the Landscape of Ampere GPU Memory Errors

Authors: Zhu Zhu, Yu Sun, Dhatri Parakal, Bo Fang, Steven Farrell, Gregory H. Bauer, Brett Bode, Ian T. Foster, Michael E. Papka, William Gropp, Zhao Zhang, Lishan Yang

Abstract: Graphics Processing Units (GPUs) have become a de facto solution for accelerating high-performance computing (HPC) applications. Understanding their memory error behavior is an essential step toward achieving efficient and reliable HPC systems. In this work, we present a large-scale cross-supercomputer study to characterize GPU memory reliability, covering three supercomputers - Delta, Polaris, an… ▽ More Graphics Processing Units (GPUs) have become a de facto solution for accelerating high-performance computing (HPC) applications. Understanding their memory error behavior is an essential step toward achieving efficient and reliable HPC systems. In this work, we present a large-scale cross-supercomputer study to characterize GPU memory reliability, covering three supercomputers - Delta, Polaris, and Perlmutter - all equipped with NVIDIA A100 GPUs. We examine error logs spanning 67.77 million GPU device-hours across 10,693 GPUs. We compare error rates and mean-time-between-errors (MTBE) and highlight both shared and distinct error characteristics among these three systems. Based on these observations and analyses, we discuss the implications and lessons learned, focusing on the reliable operation of supercomputers, the choice of checkpointing interval, and the comparison of reliability characteristics with those of previous-generation GPUs. Our characterization study provides valuable insights into fault-tolerant HPC system design and operation, enabling more efficient execution of HPC applications. △ Less

Submitted 3 September, 2025; v1 submitted 5 August, 2025; originally announced August 2025.

2024 NSF CSSI-Cybertraining-SCIPE PI Meeting August 12 to 13, 2024, Charlotte, NC

Authors: Abani Patra, Mary Thomas, Elias Bou-Harb, Jeffrey Carver, Yuebin Guo, Ratnesh Kumar, Julien Langou, Guoyu Lu, Vivak Patel, Marianna Safronova, Isla Simpson, Dhruva Chakravorty, Jane Combs, Hantao Cui, Sushil Prasad, Adnan Rajib, Susan Rathbun, Erik Saule, Isla Simpson, Alan Sussman, Shaowen Wang, Sarina Zhe Zhang, Ben Brown, Varun Chandola, Daniel Crawford , et al. (10 additional authors not shown)

Abstract: The second annual NSF, OAC CSSI, CyberTraining and related programs PI meeting was held August 12 to 13 in Charlotte, NC, with participation from PIs or representatives of all major awards. Keynotes, panels, breakouts, and poster sessions allowed PIs to engage with each other, NSF staff, and invited experts. The 286 attendees represented 292 awards across CSSI, CyberTraining, OAC Core, CIP, SCIPE… ▽ More The second annual NSF, OAC CSSI, CyberTraining and related programs PI meeting was held August 12 to 13 in Charlotte, NC, with participation from PIs or representatives of all major awards. Keynotes, panels, breakouts, and poster sessions allowed PIs to engage with each other, NSF staff, and invited experts. The 286 attendees represented 292 awards across CSSI, CyberTraining, OAC Core, CIP, SCIPE CDSE, and related programs, and presented over 250 posters. This report documents the meetings structure, findings, and recommendations, offering a snapshot of current community perspectives on cyberinfrastructure. A key takeaway is a vibrant, engaged community advancing science through CI. AI-driven research modalities complement established HPC and data centric tools. Workforce development efforts align well with the CSSI community. △ Less

Submitted 5 July, 2025; originally announced July 2025.

Comments: Annual NSF PI meeting; contains summaries of meetings and breakout sessions, lists of participants, links to presented posters on figshare

DynoStore: A wide-area distribution system for the management of data over heterogeneous storage

Authors: Dante D. Sanchez-Gallegos, J. L. Gonzalez-Compean, Maxime Gonthier, Valerie Hayot-Sasson, J. Gregory Pauloski, Haochen Pan, Kyle Chard, Jesus Carretero, Ian Foster

Abstract: Data distribution across different facilities offers benefits such as enhanced resource utilization, increased resilience through replication, and improved performance by processing data near its source. However, managing such data is challenging due to heterogeneous access protocols, disparate authentication models, and the lack of a unified coordination framework. This paper presents DynoStore,… ▽ More Data distribution across different facilities offers benefits such as enhanced resource utilization, increased resilience through replication, and improved performance by processing data near its source. However, managing such data is challenging due to heterogeneous access protocols, disparate authentication models, and the lack of a unified coordination framework. This paper presents DynoStore, a system that manages data across heterogeneous storage systems. At the core of DynoStore are data containers, an abstraction that provides standardized interfaces for seamless data management, irrespective of the underlying storage systems. Multiple data container connections create a cohesive wide-area storage network, ensuring resilience using erasure coding policies. Furthermore, a load-balancing algorithm ensures equitable and efficient utilization of storage resources. We evaluate DynoStore using benchmarks and real-world case studies, including the management of medical and satellite data across geographically distributed environments. Our results demonstrate a 10\% performance improvement compared to centralized cloud-hosted systems while maintaining competitive performance with state-of-the-art solutions such as Redis and IPFS. DynoStore also exhibits superior fault tolerance, withstanding more failures than traditional systems. △ Less

Submitted 1 July, 2025; originally announced July 2025.

Comments: 10 pages. Conference: The 25th IEEE International Symposium on Cluster, Cloud, and Internet Computing

A Grassroots Network and Community Roadmap for Interconnected Autonomous Science Laboratories for Accelerated Discovery

Authors: Rafael Ferreira da Silva, Milad Abolhasani, Dionysios A. Antonopoulos, Laura Biven, Ryan Coffee, Ian T. Foster, Leslie Hamilton, Shantenu Jha, Theresa Mayer, Benjamin Mintz, Robert G. Moore, Salahudin Nimer, Noah Paulson, Woong Shin, Frederic Suter, Mitra Taheri, Michela Taufer, Newell R. Washburn

Abstract: Scientific discovery is being revolutionized by AI and autonomous systems, yet current autonomous laboratories remain isolated islands unable to collaborate across institutions. We present the Autonomous Interconnected Science Lab Ecosystem (AISLE), a grassroots network transforming fragmented capabilities into a unified system that shorten the path from ideation to innovation to impact and accele… ▽ More Scientific discovery is being revolutionized by AI and autonomous systems, yet current autonomous laboratories remain isolated islands unable to collaborate across institutions. We present the Autonomous Interconnected Science Lab Ecosystem (AISLE), a grassroots network transforming fragmented capabilities into a unified system that shorten the path from ideation to innovation to impact and accelerates discovery from decades to months. AISLE addresses five critical dimensions: (1) cross-institutional equipment orchestration, (2) intelligent data management with FAIR compliance, (3) AI-agent driven orchestration grounded in scientific principles, (4) interoperable agent communication interfaces, and (5) AI/ML-integrated scientific education. By connecting autonomous agents across institutional boundaries, autonomous science can unlock research spaces inaccessible to traditional approaches while democratizing cutting-edge technologies. This paradigm shift toward collaborative autonomous science promises breakthroughs in sustainable energy, materials development, and public health. △ Less

Submitted 20 June, 2025; originally announced June 2025.

D-Rex: Heterogeneity-Aware Reliability Framework and Adaptive Algorithms for Distributed Storage

Authors: Maxime Gonthier, Dante D. Sanchez-Gallegos, Haochen Pan, Bogdan Nicolae, Sicheng Zhou, Hai Duc Nguyen, Valerie Hayot-Sasson, J. Gregory Pauloski, Jesus Carretero, Kyle Chard, Ian Foster

Abstract: The exponential growth of data necessitates distributed storage models, such as peer-to-peer systems and data federations. While distributed storage can reduce costs and increase reliability, the heterogeneity in storage capacity, I/O performance, and failure rates of storage resources makes their efficient use a challenge. Further, node failures are common and can lead to data unavailability and… ▽ More The exponential growth of data necessitates distributed storage models, such as peer-to-peer systems and data federations. While distributed storage can reduce costs and increase reliability, the heterogeneity in storage capacity, I/O performance, and failure rates of storage resources makes their efficient use a challenge. Further, node failures are common and can lead to data unavailability and even data loss. Erasure coding is a common resiliency strategy implemented in storage systems to mitigate failures by striping data across storage locations. However, erasure coding is computationally expensive and existing systems do not consider the heterogeneous resources and their varied capacity and performance when placing data chunks. We tackle the challenges of using erasure coding with distributed and heterogeneous nodes, aiming to store as much data as possible, minimize encoding and decoding time, and meeting user-defined reliability requirements for each data item. We propose two new dynamic scheduling algorithms, D-Rex LB and D-Rex SC, that adaptively choose erasure coding parameters and map chunks to heterogeneous nodes. D-Rex SC achieves robust performance for both storage utilization and throughput, at a higher computational cost, while D-Rex LB is faster but with slightly less competitive performance. In addition, we propose two greedy algorithms, GreedyMinStorage and GreedyLeastUsed, that optimize for storage utilization and load balancing, respectively. Our experimental evaluation shows that our dynamic schedulers store, on average, 45% more data items without significantly degrading I/O throughput compared to state-of-the-art algorithms, while GreedyLeastUsed is able to store 21% more data items while also increasing throughput. △ Less

Submitted 29 May, 2025; originally announced June 2025.

Comments: Will be published at 2025 International Conference on Supercomputing, Salt Lake City, UT, USA

Trustworthy Provenance for Big Data Science: a Modular Architecture Leveraging Blockchain in Federated Settings

Authors: Nicola Giuseppe Marchioro, Yannis Velegrakis, Valentine Anantharaj, Ian Foster, Sandro Luigi Fiore

Abstract: Ensuring the trustworthiness and long-term verifiability of scientific data is a foundational challenge in the era of data-intensive, collaborative research. Provenance metadata plays a key role in this context, capturing the origin, transformation, and usage of research artifacts. However, existing solutions often fall short when applied to distributed, multi-institutional settings. This paper in… ▽ More Ensuring the trustworthiness and long-term verifiability of scientific data is a foundational challenge in the era of data-intensive, collaborative research. Provenance metadata plays a key role in this context, capturing the origin, transformation, and usage of research artifacts. However, existing solutions often fall short when applied to distributed, multi-institutional settings. This paper introduces a modular, domain-agnostic architecture for provenance tracking in federated environments, leveraging permissioned blockchain infrastructure to guarantee integrity, immutability, and auditability. The system supports decentralized interaction, persistent identifiers for artifact traceability, and a provenance versioning model that preserves the history of updates. Designed to interoperate with diverse scientific domains, the architecture promotes transparency, accountability, and reproducibility across organizational boundaries. Ongoing work focuses on validating the system through a distributed prototype and exploring its performance in collaborative settings. △ Less

Submitted 30 May, 2025; originally announced May 2025.

AERO: An autonomous platform for continuous research

Authors: Valérie Hayot-Sasson, Abby Stevens, Nicholson Collier, Sudershan Sridhar, Kyle Conroy, J. Gregory Pauloski, Yadu Babuji, Maxime Gonthier, Nathaniel Hudson, Dante D. Sanchez-Gallegos, Ian Foster, Jonathan Ozik, Kyle Chard

Abstract: The COVID-19 pandemic highlighted the need for new data infrastructure, as epidemiologists and public health workers raced to harness rapidly evolving data, analytics, and infrastructure in support of cross-sector investigations. To meet this need, we developed AERO, an automated research and data sharing platform for continuous, distributed, and multi-disciplinary collaboration. In this paper, we… ▽ More The COVID-19 pandemic highlighted the need for new data infrastructure, as epidemiologists and public health workers raced to harness rapidly evolving data, analytics, and infrastructure in support of cross-sector investigations. To meet this need, we developed AERO, an automated research and data sharing platform for continuous, distributed, and multi-disciplinary collaboration. In this paper, we describe the AERO design and how it supports the automatic ingestion, validation, and transformation of monitored data into a form suitable for analysis; the automated execution of analyses on this data; and the sharing of data among different entities. We also describe how our AERO implementation leverages capabilities provided by the Globus platform and GitHub for automation, distributed execution, data sharing, and authentication. We present results obtained with an instance of AERO running two public health surveillance applications and demonstrate benchmarking results with a synthetic application, all of which are publicly available for testing. △ Less

Submitted 23 May, 2025; originally announced May 2025.

Topology-Aware Knowledge Propagation in Decentralized Learning

Authors: Mansi Sakarvadia, Nathaniel Hudson, Tian Li, Ian Foster, Kyle Chard

Abstract: Decentralized learning enables collaborative training of models across naturally distributed data without centralized coordination or maintenance of a global model. Instead, devices are organized in arbitrary communication topologies, in which they can only communicate with neighboring devices. Each device maintains its own local model by training on its local data and integrating new knowledge vi… ▽ More Decentralized learning enables collaborative training of models across naturally distributed data without centralized coordination or maintenance of a global model. Instead, devices are organized in arbitrary communication topologies, in which they can only communicate with neighboring devices. Each device maintains its own local model by training on its local data and integrating new knowledge via model aggregation with neighbors. Therefore, knowledge is propagated across the topology via successive aggregation rounds. We study, in particular, the propagation of out-of-distribution (OOD) knowledge. We find that popular decentralized learning algorithms struggle to propagate OOD knowledge effectively to all devices. Further, we find that both the location of OOD data within a topology, and the topology itself, significantly impact OOD knowledge propagation. We then propose topology-aware aggregation strategies to accelerate (OOD) knowledge propagation across devices. These strategies improve OOD data accuracy, compared to topology-unaware baselines, by 123% on average across models in a topology. △ Less

Submitted 16 May, 2025; originally announced May 2025.

Empowering Scientific Workflows with Federated Agents

Authors: Alok Kamatar, J. Gregory Pauloski, Yadu Babuji, Ryan Chard, Mansi Sakarvadia, Daniel Babnigg, Kyle Chard, Ian Foster

Abstract: Agentic systems, in which diverse agents cooperate to tackle challenging problems, are exploding in popularity in the AI community. However, existing agentic frameworks take a relatively narrow view of agents, apply a centralized model, and target conversational, cloud-native applications (e.g., LLM-based AI chatbots). In contrast, scientific applications require myriad agents be deployed and mana… ▽ More Agentic systems, in which diverse agents cooperate to tackle challenging problems, are exploding in popularity in the AI community. However, existing agentic frameworks take a relatively narrow view of agents, apply a centralized model, and target conversational, cloud-native applications (e.g., LLM-based AI chatbots). In contrast, scientific applications require myriad agents be deployed and managed across diverse cyberinfrastructure. Here we introduce Academy, a modular and extensible middleware designed to deploy autonomous agents across the federated research ecosystem, including HPC systems, experimental facilities, and data repositories. To meet the demands of scientific computing, Academy supports asynchronous execution, heterogeneous resources, high-throughput data flows, and dynamic resource availability. It provides abstractions for expressing stateful agents, managing inter-agent coordination, and integrating computation with experimental control. We present microbenchmark results that demonstrate high performance and scalability in HPC environments. To explore the breadth of applications that can be supported by agentic workflow designs, we also present case studies in materials discovery, astronomy, decentralized learning, and information extraction in which agents are deployed across diverse HPC systems. △ Less

Submitted 29 January, 2026; v1 submitted 8 May, 2025; originally announced May 2025.

Comments: To appear at the IEEE International Parallel & Distributed Processing Symposium (IPDPS '26)

HiPerRAG: High-Performance Retrieval Augmented Generation for Scientific Insights

Authors: Ozan Gokdemir, Carlo Siebenschuh, Alexander Brace, Azton Wells, Brian Hsu, Kyle Hippe, Priyanka V. Setty, Aswathy Ajith, J. Gregory Pauloski, Varuni Sastry, Sam Foreman, Huihuo Zheng, Heng Ma, Bharat Kale, Nicholas Chia, Thomas Gibbs, Michael E. Papka, Thomas Brettin, Francis J. Alexander, Anima Anandkumar, Ian Foster, Rick Stevens, Venkatram Vishwanath, Arvind Ramanathan

Abstract: The volume of scientific literature is growing exponentially, leading to underutilized discoveries, duplicated efforts, and limited cross-disciplinary collaboration. Retrieval Augmented Generation (RAG) offers a way to assist scientists by improving the factuality of Large Language Models (LLMs) in processing this influx of information. However, scaling RAG to handle millions of articles introduce… ▽ More The volume of scientific literature is growing exponentially, leading to underutilized discoveries, duplicated efforts, and limited cross-disciplinary collaboration. Retrieval Augmented Generation (RAG) offers a way to assist scientists by improving the factuality of Large Language Models (LLMs) in processing this influx of information. However, scaling RAG to handle millions of articles introduces significant challenges, including the high computational costs associated with parsing documents and embedding scientific knowledge, as well as the algorithmic complexity of aligning these representations with the nuanced semantics of scientific content. To address these issues, we introduce HiPerRAG, a RAG workflow powered by high performance computing (HPC) to index and retrieve knowledge from more than 3.6 million scientific articles. At its core are Oreo, a high-throughput model for multimodal document parsing, and ColTrast, a query-aware encoder fine-tuning algorithm that enhances retrieval accuracy by using contrastive learning and late-interaction techniques. HiPerRAG delivers robust performance on existing scientific question answering benchmarks and two new benchmarks introduced in this work, achieving 90% accuracy on SciQ and 76% on PubMedQA-outperforming both domain-specific models like PubMedGPT and commercial LLMs such as GPT-4. Scaling to thousands of GPUs on the Polaris, Sunspot, and Frontier supercomputers, HiPerRAG delivers million document-scale RAG workflows for unifying scientific knowledge and fostering interdisciplinary innovation. △ Less

Submitted 7 May, 2025; originally announced May 2025.

Comments: This paper has been accepted at the Platform for Advanced Scientific Computing Conference (PASC 25), June 16-18, 2025, Brugg-Windisch, Switzerland

ACM Class: H.3.3; I.2.7

34 Examples of LLM Applications in Materials Science and Chemistry: Towards Automation, Assistants, Agents, and Accelerated Scientific Discovery

Authors: Yoel Zimmermann, Adib Bazgir, Alexander Al-Feghali, Mehrad Ansari, Joshua Bocarsly, L. Catherine Brinson, Yuan Chiang, Defne Circi, Min-Hsueh Chiu, Nathan Daelman, Matthew L. Evans, Abhijeet S. Gangan, Janine George, Hassan Harb, Ghazal Khalighinejad, Sartaaj Takrim Khan, Sascha Klawohn, Magdalena Lederbauer, Soroush Mahjoubi, Bernadette Mohr, Seyed Mohamad Moosavi, Aakash Naik, Aleyna Beste Ozhan, Dieter Plessers, Aritra Roy , et al. (10 additional authors not shown)

Abstract: Large Language Models (LLMs) are reshaping many aspects of materials science and chemistry research, enabling advances in molecular property prediction, materials design, scientific automation, knowledge extraction, and more. Recent developments demonstrate that the latest class of models are able to integrate structured and unstructured data, assist in hypothesis generation, and streamline resear… ▽ More Large Language Models (LLMs) are reshaping many aspects of materials science and chemistry research, enabling advances in molecular property prediction, materials design, scientific automation, knowledge extraction, and more. Recent developments demonstrate that the latest class of models are able to integrate structured and unstructured data, assist in hypothesis generation, and streamline research workflows. To explore the frontier of LLM capabilities across the research lifecycle, we review applications of LLMs through 34 total projects developed during the second annual Large Language Model Hackathon for Applications in Materials Science and Chemistry, a global hybrid event. These projects spanned seven key research areas: (1) molecular and material property prediction, (2) molecular and material design, (3) automation and novel interfaces, (4) scientific communication and education, (5) research data management and automation, (6) hypothesis generation and evaluation, and (7) knowledge extraction and reasoning from the scientific literature. Collectively, these applications illustrate how LLMs serve as versatile predictive models, platforms for rapid prototyping of domain-specific tools, and much more. In particular, improvements in both open source and proprietary LLM performance through the addition of reasoning, additional training data, and new techniques have expanded effectiveness, particularly in low-data environments and interdisciplinary research. As LLMs continue to improve, their integration into scientific workflows presents both new opportunities and new challenges, requiring ongoing exploration, continued refinement, and further research to address reliability, interpretability, and reproducibility. △ Less

Submitted 15 May, 2025; v1 submitted 5 May, 2025; originally announced May 2025.

Comments: arXiv admin note: substantial text overlap with arXiv:2411.15221. This paper is a refinement and analysis of the raw project submissions from arXiv:2411.15221

AdaParse: An Adaptive Parallel PDF Parsing and Resource Scaling Engine

Authors: Carlo Siebenschuh, Kyle Hippe, Ozan Gokdemir, Alexander Brace, Arham Khan, Khalid Hossain, Yadu Babuji, Nicholas Chia, Venkatram Vishwanath, Rick Stevens, Arvind Ramanathan, Ian Foster, Robert Underwood

Abstract: Language models for scientific tasks are trained on text from scientific publications, most distributed as PDFs that require parsing. PDF parsing approaches range from inexpensive heuristics (for simple documents) to computationally intensive ML-driven systems (for complex or degraded ones). The choice of the "best" parser for a particular document depends on its computational cost and the accurac… ▽ More Language models for scientific tasks are trained on text from scientific publications, most distributed as PDFs that require parsing. PDF parsing approaches range from inexpensive heuristics (for simple documents) to computationally intensive ML-driven systems (for complex or degraded ones). The choice of the "best" parser for a particular document depends on its computational cost and the accuracy of its output. To address these issues, we introduce an Adaptive Parallel PDF Parsing and Resource Scaling Engine (AdaParse), a data-driven strategy for assigning an appropriate parser to each document. We enlist scientists to select preferred parser outputs and incorporate this information through direct preference optimization (DPO) into AdaParse, thereby aligning its selection process with human judgment. AdaParse then incorporates hardware requirements and predicted accuracy of each parser to orchestrate computational resources efficiently for large-scale parsing campaigns. We demonstrate that AdaParse, when compared to state-of-the-art parsers, improves throughput by $17\times$ while still achieving comparable accuracy (0.2 percent better) on a benchmark set of 1000 scientific documents. AdaParse's combination of high accuracy and parallel scalability makes it feasible to parse large-scale scientific document corpora to support the development of high-quality, trillion-token-scale text datasets. The implementation is available at https://github.com/7shoe/AdaParse/ △ Less

Submitted 23 April, 2025; originally announced May 2025.

Comments: This paper has been accepted at the The Eighth Annual Conference on Machine Learning and Systems (MLSys 2025)

Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems

Authors: Bang Liu, Xinfeng Li, Jiayi Zhang, Jinlin Wang, Tanjin He, Sirui Hong, Hongzhang Liu, Shaokun Zhang, Kaitao Song, Kunlun Zhu, Yuheng Cheng, Suyuchen Wang, Xiaoqiang Wang, Yuyu Luo, Haibo Jin, Peiyan Zhang, Ollie Liu, Jiaqi Chen, Huan Zhang, Zhaoyang Yu, Haochen Shi, Boyan Li, Dekun Wu, Fengwei Teng, Xiaojun Jia , et al. (23 additional authors not shown)

Abstract: The advent of large language models (LLMs) has catalyzed a transformative shift in artificial intelligence, paving the way for advanced intelligent agents capable of sophisticated reasoning, robust perception, and versatile action across diverse domains. As these agents increasingly drive AI research and practical applications, their design, evaluation, and continuous improvement present intricate… ▽ More The advent of large language models (LLMs) has catalyzed a transformative shift in artificial intelligence, paving the way for advanced intelligent agents capable of sophisticated reasoning, robust perception, and versatile action across diverse domains. As these agents increasingly drive AI research and practical applications, their design, evaluation, and continuous improvement present intricate, multifaceted challenges. This book provides a comprehensive overview, framing intelligent agents within modular, brain-inspired architectures that integrate principles from cognitive science, neuroscience, and computational research. We structure our exploration into four interconnected parts. First, we systematically investigate the modular foundation of intelligent agents, systematically mapping their cognitive, perceptual, and operational modules onto analogous human brain functionalities and elucidating core components such as memory, world modeling, reward processing, goal, and emotion. Second, we discuss self-enhancement and adaptive evolution mechanisms, exploring how agents autonomously refine their capabilities, adapt to dynamic environments, and achieve continual learning through automated optimization paradigms. Third, we examine multi-agent systems, investigating the collective intelligence emerging from agent interactions, cooperation, and societal structures. Finally, we address the critical imperative of building safe and beneficial AI systems, emphasizing intrinsic and extrinsic security threats, ethical alignment, robustness, and practical mitigation strategies necessary for trustworthy real-world deployment. By synthesizing modular AI architectures with insights from different disciplines, this survey identifies key research challenges and opportunities, encouraging innovations that harmonize technological advancement with meaningful societal benefit. △ Less

Submitted 2 August, 2025; v1 submitted 31 March, 2025; originally announced April 2025.

Globus Service Enhancements for Exascale Applications and Facilities

Authors: Weijian Zheng, Jack Kordas, Tyler J. Skluzacek, Raj Kettimuthu, Ian Foster

Abstract: Many extreme-scale applications require the movement of large quantities of data to, from, and among leadership computing facilities, as well as other scientific facilities and the home institutions of facility users. These applications, particularly when leadership computing facilities are involved, can touch upon edge cases (e.g., terabyte files) that had not been a focus of previous Globus opti… ▽ More Many extreme-scale applications require the movement of large quantities of data to, from, and among leadership computing facilities, as well as other scientific facilities and the home institutions of facility users. These applications, particularly when leadership computing facilities are involved, can touch upon edge cases (e.g., terabyte files) that had not been a focus of previous Globus optimization work, which had emphasized rather the movement of many smaller (megabyte to gigabyte) files. We report here on how automated client-driven chunking can be used to accelerate both the movement of large files and the integrity checking operations that have proven to be essential for large data transfers. We present detailed performance studies that provide insights into the benefits of these modifications in a range of file transfer scenarios. △ Less

Submitted 29 March, 2025; originally announced March 2025.

WRATH: Workload Resilience Across Task Hierarchies in Task-based Parallel Programming Frameworks

Authors: Sicheng Zhou, Zhuozhao Li, Valérie Hayot-Sasson, Haochen Pan, Maxime Gonthier, J. Gregory Pauloski, Ryan Chard, Kyle Chard, Ian Foster

Abstract: Failures in Task-based Parallel Programming (TBPP) can severely degrade performance and result in incomplete or incorrect outcomes. Existing failure-handling approaches, including reactive, proactive, and resilient methods such as retry and checkpointing mechanisms, often apply uniform retry mechanisms regardless of the root cause of failures, failing to account for the unique characteristics of T… ▽ More Failures in Task-based Parallel Programming (TBPP) can severely degrade performance and result in incomplete or incorrect outcomes. Existing failure-handling approaches, including reactive, proactive, and resilient methods such as retry and checkpointing mechanisms, often apply uniform retry mechanisms regardless of the root cause of failures, failing to account for the unique characteristics of TBPP frameworks such as heterogeneous resource availability and task-level failures. To address these limitations, we propose WRATH, a novel systematic approach that categorizes failures based on the unique layered structure of TBPP frameworks and defines specific responses to address failures at different layers. WRATH combines a distributed monitoring system and a resilient module to collaboratively address different types of failures in real time. The monitoring system captures execution and resource information, reports failures, and profiles tasks across different layers of TBPP frameworks. The resilient module then categorizes failures and responds with appropriate actions, such as hierarchically retrying failed tasks on suitable resources. Evaluations demonstrate that WRATH significantly improves TBPP robustness, tripling the task success rate and maintaining an application success rate of over 90% for resolvable failures. Additionally, WRATH can reduce the time to failure by 20%-50%, allowing tasks that are destined to fail to be identified and fail more quickly. △ Less

Submitted 27 March, 2025; v1 submitted 16 March, 2025; originally announced March 2025.

Comments: Preprint version

EAIRA: Establishing a Methodology for Evaluating AI Models as Scientific Research Assistants

Authors: Franck Cappello, Sandeep Madireddy, Robert Underwood, Neil Getty, Nicholas Lee-Ping Chia, Nesar Ramachandra, Josh Nguyen, Murat Keceli, Tanwi Mallick, Zilinghan Li, Marieme Ngom, Chenhui Zhang, Angel Yanguas-Gil, Evan Antoniuk, Bhavya Kailkhura, Minyang Tian, Yufeng Du, Yuan-Sen Ting, Azton Wells, Bogdan Nicolae, Avinash Maurya, M. Mustafa Rafique, Eliu Huerta, Bo Li, Ian Foster , et al. (1 additional authors not shown)

Abstract: Recent advancements have positioned AI, and particularly Large Language Models (LLMs), as transformative tools for scientific research, capable of addressing complex tasks that require reasoning, problem-solving, and decision-making. Their exceptional capabilities suggest their potential as scientific research assistants but also highlight the need for holistic, rigorous, and domain-specific evalu… ▽ More Recent advancements have positioned AI, and particularly Large Language Models (LLMs), as transformative tools for scientific research, capable of addressing complex tasks that require reasoning, problem-solving, and decision-making. Their exceptional capabilities suggest their potential as scientific research assistants but also highlight the need for holistic, rigorous, and domain-specific evaluation to assess effectiveness in real-world scientific applications. This paper describes a multifaceted methodology for Evaluating AI models as scientific Research Assistants (EAIRA) developed at Argonne National Laboratory. This methodology incorporates four primary classes of evaluations. 1) Multiple Choice Questions to assess factual recall; 2) Open Response to evaluate advanced reasoning and problem-solving skills; 3) Lab-Style Experiments involving detailed analysis of capabilities as research assistants in controlled environments; and 4) Field-Style Experiments to capture researcher-LLM interactions at scale in a wide range of scientific domains and applications. These complementary methods enable a comprehensive analysis of LLM strengths and weaknesses with respect to their scientific knowledge, reasoning abilities, and adaptability. Recognizing the rapid pace of LLM advancements, we designed the methodology to evolve and adapt so as to ensure its continued relevance and applicability. This paper describes the methodology state at the end of February 2025. Although developed within a subset of scientific domains, the methodology is designed to be generalizable to a wide range of scientific domains. △ Less

Submitted 27 February, 2025; originally announced February 2025.

Comments: 33 pages, 18 figures

Connecting Large Language Model Agent to High Performance Computing Resource

Authors: Heng Ma, Alexander Brace, Carlo Siebenschuh, Greg Pauloski, Ian Foster, Arvind Ramanathan

Abstract: The Large Language Model agent workflow enables the LLM to invoke tool functions to increase the performance on specific scientific domain questions. To tackle large scale of scientific research, it requires access to computing resource and parallel computing setup. In this work, we implemented Parsl to the LangChain/LangGraph tool call setup, to bridge the gap between the LLM agent to the computi… ▽ More The Large Language Model agent workflow enables the LLM to invoke tool functions to increase the performance on specific scientific domain questions. To tackle large scale of scientific research, it requires access to computing resource and parallel computing setup. In this work, we implemented Parsl to the LangChain/LangGraph tool call setup, to bridge the gap between the LLM agent to the computing resource. Two tool call implementations were set up and tested on both local workstation and HPC environment on Polaris/ALCF. The first implementation with Parsl-enabled LangChain tool node queues the tool functions concurrently to the Parsl workers for parallel execution. The second configuration is implemented by converting the tool functions into Parsl ensemble functions, and is more suitable for large task on super computer environment. The LLM agent workflow was prompted to run molecular dynamics simulations, with different protein structure and simulation conditions. These results showed the LLM agent tools were managed and executed concurrently by Parsl on the available computing resource. △ Less

Submitted 17 February, 2025; originally announced February 2025.

Comments: 7 pages, 4 figures

ACM Class: I.2.11

DrugImproverGPT: A Large Language Model for Drug Optimization with Fine-Tuning via Structured Policy Optimization

Authors: Xuefeng Liu, Songhao Jiang, Siyu Chen, Zhuoran Yang, Yuxin Chen, Ian Foster, Rick Stevens

Abstract: Finetuning a Large Language Model (LLM) is crucial for generating results towards specific objectives. This research delves into the realm of drug optimization and introduce a novel reinforcement learning algorithm to finetune a drug optimization LLM-based generative model, enhancing the original drug across target objectives, while retains the beneficial chemical properties of the original drug.… ▽ More Finetuning a Large Language Model (LLM) is crucial for generating results towards specific objectives. This research delves into the realm of drug optimization and introduce a novel reinforcement learning algorithm to finetune a drug optimization LLM-based generative model, enhancing the original drug across target objectives, while retains the beneficial chemical properties of the original drug. This work is comprised of two primary components: (1) DrugImprover: A framework tailored for improving robustness and efficiency in drug optimization. It includes a LLM designed for drug optimization and a novel Structured Policy Optimization (SPO) algorithm, which is theoretically grounded. This algorithm offers a unique perspective for fine-tuning the LLM-based generative model by aligning the improvement of the generated molecule with the input molecule under desired objectives. (2) A dataset of 1 million compounds, each with OEDOCK docking scores on 5 human proteins associated with cancer cells and 24 binding sites from SARS-CoV-2 virus. We conduct a comprehensive evaluation of SPO and demonstrate its effectiveness in improving the original drug across target properties. Our code and dataset will be publicly available at: https://github.com/xuefeng-cs/DrugImproverGPT. △ Less

Submitted 10 February, 2025; originally announced February 2025.

ScaffoldGPT: A Scaffold-based GPT Model for Drug Optimization

Authors: Xuefeng Liu, Songhao Jiang, Ian Foster, Jinbo Xu, Rick Stevens

Abstract: Drug optimization has become increasingly crucial in light of fast-mutating virus strains and drug-resistant cancer cells. Nevertheless, it remains challenging as it necessitates retaining the beneficial properties of the original drug while simultaneously enhancing desired attributes beyond its scope. In this work, we aim to tackle this challenge by introducing ScaffoldGPT, a novel Generative Pre… ▽ More Drug optimization has become increasingly crucial in light of fast-mutating virus strains and drug-resistant cancer cells. Nevertheless, it remains challenging as it necessitates retaining the beneficial properties of the original drug while simultaneously enhancing desired attributes beyond its scope. In this work, we aim to tackle this challenge by introducing ScaffoldGPT, a novel Generative Pretrained Transformer (GPT) designed for drug optimization based on molecular scaffolds. Our work comprises three key components: (1) A three-stage drug optimization approach that integrates pretraining, finetuning, and decoding optimization. (2) A novel two-phase incremental pre-training strategy for scaffold-based drug optimization. (3) A token-level decoding optimization strategy, Top-N, that enabling controlled, reward-guided generation using the pretrained or finetuned GPT. We demonstrate via a comprehensive evaluation on COVID and cancer benchmarks that ScaffoldGPT outperforms the competing baselines in drug optimization benchmarks, while excelling in preserving original functional scaffold and enhancing desired properties. △ Less

Submitted 10 August, 2025; v1 submitted 9 February, 2025; originally announced February 2025.

Optimizing Fine-Grained Parallelism Through Dynamic Load Balancing on Multi-Socket Many-Core Systems

Authors: Wenyi Wang, Maxime Gonthier, Poornima Nookala, Haochen Pan, Ian Foster, Ioan Raicu, Kyle Chard

Abstract: Achieving efficient task parallelism on many-core architectures is an important challenge. The widely used GNU OpenMP implementation of the popular OpenMP parallel programming model incurs high overhead for fine-grained, short-running tasks due to time spent on runtime synchronization. In this work, we introduce and analyze three key advances that collectively achieve significant performance gains… ▽ More Achieving efficient task parallelism on many-core architectures is an important challenge. The widely used GNU OpenMP implementation of the popular OpenMP parallel programming model incurs high overhead for fine-grained, short-running tasks due to time spent on runtime synchronization. In this work, we introduce and analyze three key advances that collectively achieve significant performance gains. First, we introduce XQueue, a lock-less concurrent queue implementation to replace GNU's priority task queue and remove the global task lock. Second, we develop a scalable, efficient, and hybrid lock-free/lock-less distributed tree barrier to address the high hardware synchronization overhead from GNU's centralized barrier. Third, we develop two lock-less and NUMA-aware load balancing strategies. We evaluate our implementation using Barcelona OpenMP Task Suite (BOTS) benchmarks. We show that the use of XQueue and the distributed tree barrier can improve performance by up to 1522.8$\times$ compared to the original GNU OpenMP. We further show that lock-less load balancing can improve performance by up to 4$\times$ compared to GNU OpenMP using XQueue. △ Less

Submitted 19 March, 2025; v1 submitted 7 February, 2025; originally announced February 2025.

Comments: 13 pages, 11 figures, camera-ready, accepted by IPDPS2025

ACM Class: D.1.3

MOFA: Discovering Materials for Carbon Capture with a GenAI- and Simulation-Based Workflow

Authors: Xiaoli Yan, Nathaniel Hudson, Hyun Park, Daniel Grzenda, J. Gregory Pauloski, Marcus Schwarting, Haochen Pan, Hassan Harb, Samuel Foreman, Chris Knight, Tom Gibbs, Kyle Chard, Santanu Chaudhuri, Emad Tajkhorshid, Ian Foster, Mohamad Moosavi, Logan Ward, E. A. Huerta

Abstract: We present MOFA, an open-source generative AI (GenAI) plus simulation workflow for high-throughput generation of metal-organic frameworks (MOFs) on large-scale high-performance computing (HPC) systems. MOFA addresses key challenges in integrating GPU-accelerated computing for GPU-intensive GenAI tasks, including distributed training and inference, alongside CPU- and GPU-optimized tasks for screeni… ▽ More We present MOFA, an open-source generative AI (GenAI) plus simulation workflow for high-throughput generation of metal-organic frameworks (MOFs) on large-scale high-performance computing (HPC) systems. MOFA addresses key challenges in integrating GPU-accelerated computing for GPU-intensive GenAI tasks, including distributed training and inference, alongside CPU- and GPU-optimized tasks for screening and filtering AI-generated MOFs using molecular dynamics, density functional theory, and Monte Carlo simulations. These heterogeneous tasks are unified within an online learning framework that optimizes the utilization of available CPU and GPU resources across HPC systems. Performance metrics from a 450-node (14,400 AMD Zen 3 CPUs + 1800 NVIDIA A100 GPUs) supercomputer run demonstrate that MOFA achieves high-throughput generation of novel MOF structures, with CO$_2$ adsorption capacities ranking among the top 10 in the hypothetical MOF (hMOF) dataset. Furthermore, the production of high-quality MOFs exhibits a linear relationship with the number of nodes utilized. The modular architecture of MOFA will facilitate its integration into other scientific applications that dynamically combine GenAI with large-scale simulations. △ Less

Submitted 17 January, 2025; originally announced January 2025.

Comments: 13 pages, 10 figures

Core Hours and Carbon Credits: Incentivizing Sustainability in HPC

Authors: Alok Kamatar, Maxime Gonthier, Valerie Hayot-Sasson, Andre Bauer, Marcin Copik, Torsten Hoefler, Raul Castro Fernandez, Kyle Chard, Ian Foster

Abstract: Realizing a shared responsibility between providers and consumers is critical to manage the sustainability of HPC. However, while cost may motivate efficiency improvements by infrastructure operators, broader progress is impeded by a lack of user incentives. We conduct a survey of HPC users that reveals fewer than 30 percent are aware of their energy consumption, and that energy efficiency is amon… ▽ More Realizing a shared responsibility between providers and consumers is critical to manage the sustainability of HPC. However, while cost may motivate efficiency improvements by infrastructure operators, broader progress is impeded by a lack of user incentives. We conduct a survey of HPC users that reveals fewer than 30 percent are aware of their energy consumption, and that energy efficiency is among users' lowest priority concerns. One explanation is that existing pricing models may encourage users to prioritize performance over energy efficiency. We propose two transparent multi-resource pricing schemes, Energy- and Carbon-Based Accounting, that seek to change this paradigm by incentivizing more efficient user behavior. These two schemes charge for computations based on their energy consumption or carbon footprint, respectively, rewarding users who leverage efficient hardware and software. We evaluate these two pricing schemes via simulation, in a prototype, and a user study. △ Less

Submitted 1 December, 2025; v1 submitted 16 January, 2025; originally announced January 2025.

Computational Grids

Authors: Ian Foster, Carl Kesselman

Abstract: In this introductory chapter, we lay the groundwork for the rest of the book by providing a more detailed picture of the expected purpose, shape, and architecture of future grid systems. We structure the chapter in terms of six questions that we believe are central to this discussion: Why do we need computational grids? What types of applications will grids be used for? Who will use grids? How wil… ▽ More In this introductory chapter, we lay the groundwork for the rest of the book by providing a more detailed picture of the expected purpose, shape, and architecture of future grid systems. We structure the chapter in terms of six questions that we believe are central to this discussion: Why do we need computational grids? What types of applications will grids be used for? Who will use grids? How will grids be used? What is involved in building a grid? And, what problems must be solved to make grids commonplace? We provide an overview of each of these issues here, referring to subsequent chapters for more detailed discussion. △ Less

Submitted 2 January, 2025; originally announced January 2025.

Comments: Chapter 2 of the book, "The Grid: Blueprint for a New Computing Infrastructure", Elsevier, 1998