Tootfinder

UltraHorizon: Benchmarking Agent Capabilities in Ultra Long-Horizon Scenarios
Haotian Luo, Huaisong Zhang, Xuelin Zhang, Haoyu Wang, Zeyu Qin, Wenjie Lu, Guozheng Ma, Haiying He, Yingsha Xie, Qiyang Zhou, Zixuan Hu, Hongze Mi, Yibo Wang, Naiqiang Tan, Hong Chen, Yi R. Fung, Chun Yuan, Li Shen
https://arxiv.org/abs/2509.21766

UltraHorizon: Benchmarking Agent Capabilities in Ultra Long-Horizon Scenarios
Autonomous agents have recently achieved remarkable progress across diverse domains, yet most evaluations focus on short-horizon, fully observable tasks. In contrast, many critical real-world tasks, such as large-scale software development, commercial investment, and scientific discovery, unfold in long-horizon and partially observable scenarios where success hinges on sustained reasoning, planning, memory management, and tool use. Existing benchmarks rarely capture these long-horizon challenge…

Integrating and Characterizing HPC Task Runtime Systems for hybrid AI-HPC workloads
Andre Merzky, Mikhail Titov, Matteo Turilli, Shantenu Jha
https://arxiv.org/abs/2509.20819 ht…

Integrating and Characterizing HPC Task Runtime Systems for hybrid AI-HPC workloads
Scientific workflows increasingly involve both HPC and machine-learning tasks, combining MPI-based simulations, training, and inference in a single execution. Launchers such as Slurm's srun constrain concurrency and throughput, making them unsuitable for dynamic and heterogeneous workloads. We present a performance study of RADICAL-Pilot (RP) integrated with Flux and Dragon, two complementary runtime systems that enable hierarchical resource management and high-throughput function execution. Us…

Using Artificial Intuition in Distinct, Minimalist Classification of Scientific Abstracts for Management of Technology Portfolios
Prateek Ranka, Fred Morstatter, Andrea Belz, Alexandra Graddy-Reed
https://arxiv.org/abs/2508.13182

Using Artificial Intuition in Distinct, Minimalist Classification of Scientific Abstracts for Management of Technology Portfolios
Classification of scientific abstracts is useful for strategic activities but challenging to automate because the sparse text provides few contextual clues. Metadata associated with the scientific publication can be used to improve performance but still often requires a semi-supervised setting. Moreover, such schemes may generate labels that lack distinction -- namely, they overlap and thus do not uniquely define the abstract. In contrast, experts label and sort these texts with ease. Here we d…

Lightsails for Interstellar Travel - Photonics for Propulsion, Thermal Management and Stability: #lightsail endeavor one of the most promising and exciting scientific pursuits in the twenty-first century. Looking forward, further progress must be made across numerous fields of science in order to bring lightsails to the next stage of viability. [...] We see the lightsail project shifting the paradigm of space exploration in the twenty-first century, inspiring generations of scientists at the boundaries of scientific and technical capabilities."

Who Uses Whose Telescopes? Analyzing the Knowledge Geography and Research Dominance of Global Astronomical Facilities
Yue Chen (Institute of Science of Science,S&T Management,WISE Lab, Dalian University of Technology), Yuqi Wang (Institute of Science of Science,S&T Management,WISE Lab, Dalian University of Technology), Yuying Gao (Institute of Science of Science,S&T Management,WISE Lab, Dalian University of Technology), Zhiqi Wang (Institute of Science of Science,S&T Ma…

Who Uses Whose Telescopes? Analyzing the Knowledge Geography and Research Dominance of Global Astronomical Facilities
Large-scale research infrastructures (LSRIs) are central to contemporary science policy, combining massive capital investments with international access regimes. Yet whether open access to these infrastructures translates into more equitable scientific authority remains contested. Astronomy provides a critical case: world-leading observatories are globally shared but embedded in specific national contexts. We compile a novel country--year dataset (1955--2025) linking the location of astronomica…

Language Model Perplexity Predicts Scientific Surprise and Transformative Impact
Zhen Zhang (School of Information Management, Nanjing University, Knowledge Lab, University of Chicago), James Evans (Department of Sociology, University of Chicago, Santa Fe Institute)
https://arxiv.org/abs/2509.05591…

Language Model Perplexity Predicts Scientific Surprise and Transformative Impact
Scientific breakthroughs typically emerge through the surprising violation of established research ideas, yet quantifying surprise has remained elusive because it requires a coherent model of all contemporary scientific worldviews. Deep neural networks like large language models (LLMs) are arbitrary function approximators tuned to consistently expect the expressions and ideas on which they were trained and those semantically nearby. This suggests that as LLMs improve at generating plausible tex…

LLM-Based Information Extraction to Support Scientific Literature Research and Publication Workflows
Samy Ateia, Udo Kruschwitz, Melanie Scholz, Agnes Koschmider, Moayad Almohaishi
https://arxiv.org/abs/2510.04749

LLM-Based Information Extraction to Support Scientific Literature Research and Publication Workflows
The increasing volume of scholarly publications requires advanced tools for efficient knowledge discovery and management. This paper introduces ongoing work on a system using Large Language Models (LLMs) for the semantic extraction of key concepts from scientific documents. Our research, conducted within the German National Research Data Infrastructure for and with Computer Science (NFDIxCS) project, seeks to support FAIR (Findable, Accessible, Interoperable, and Reusable) principles in scienti…

IoDResearch: Deep Research on Private Heterogeneous Data via the Internet of Data
Zhuofan Shi, Zijie Guo, Xinjian Ma, Gang Huang, Yun Ma, Xiang Jing
https://arxiv.org/abs/2510.01553

IoDResearch: Deep Research on Private Heterogeneous Data via the Internet of Data
The rapid growth of multi-source, heterogeneous, and multimodal scientific data has increasingly exposed the limitations of traditional data management. Most existing DeepResearch (DR) efforts focus primarily on web search while overlooking local private data. Consequently, these frameworks exhibit low retrieval efficiency for private data and fail to comply with the FAIR principles, ultimately resulting in inefficiency and limited reusability. To this end, we propose IoDResearch (Internet of D…

iDDS: Intelligent Distributed Dispatch and Scheduling for Workflow Orchestration
Wen Guan, Tadashi Maeno, Aleksandr Alekseev, Fernando Harald Barreiro Megino, Kaushik De, Edward Karavakis, Alexei Klimentov, Tatiana Korchuganova, FaHui Lin, Paul Nilsson, Torre Wenaus, Zhaoyu Yang, Xin Zhao
https://arxiv.org/abs/2510.02930

iDDS: Intelligent Distributed Dispatch and Scheduling for Workflow Orchestration
The intelligent Distributed Dispatch and Scheduling (iDDS) service is a versatile workflow orchestration system designed for large-scale, distributed scientific computing. iDDS extends traditional workload and data management by integrating data-aware execution, conditional logic, and programmable workflows, enabling automation of complex and dynamic processing pipelines. Originally developed for the ATLAS experiment at the Large Hadron Collider, iDDS has evolved into an experiment-agnostic pla…

A Zero-Inflated Spatio-Temporal Model for Integrating Fishery-Dependent and Independent Data under Preferential Sampling
Daniela Silva, Raquel Menezes, Gon\c{c}alo Ara\'ujo, Ana Machado, Renato Rosa, Ana Moreno, Alexandra Silva, Susana Garrido
https://arxiv.org/abs/2509.09336

A Zero-Inflated Spatio-Temporal Model for Integrating Fishery-Dependent and Independent Data under Preferential Sampling
Sustainable management of marine ecosystems is vital for maintaining healthy fishery resources, and benefits from advanced scientific tools to accurately assess species distribution patterns. In fisheries science, two primary data sources are used: fishery-independent data (FID), collected through systematic surveys, and fishery-dependent data (FDD), obtained from commercial fishing activities. While these sources provide complementary information, their distinct sampling schemes - systematic f…