arXiv subjects

Charles Park

Publications and source records attributed to Charles Park.

3 recordsLinked to original sources

arXiv2025

UI-CUBE: Enterprise-Grade Computer Use Agent Benchmarking Beyond Task Accuracy to Operational Reliability

While current Computer Use Agent (CUA) benchmarks measure task completion effectively, they provide limited assessment of enterprise deployment readiness, emphasizing functional correctness over the operational reliability required for production systems. We present UI-CUBE (UiPath Computer Use BEnchmark), a systematic benchmark comprising 226 tasks across two difficulty tiers designed to expose fundamental architectural limitations in current CUAs. Our evaluation covers simple UI interactions (136 tasks) and complex workflows including copy-paste tasks (50 tasks) and enterprise application scenarios (40 tasks), with systematic interface variation coverage, multi-resolution testing and automated validation of task success through the application state. Evaluation of five state-of-the-art models reveals a sharp capability cliff rather than gradual performance degradation. Simple UI interactions achieve 67-85% success rates (compared to 97.9% human performance), but complex workflows drop precipitously to 9-19%. Human evaluators with no prior application experience achieve only 61.2% on complex tasks despite near-perfect performance on simple tasks, establishing realistic performance ceilings. This discontinuous performance pattern -- where agents achieve 68-87% of human performance on simple tasks but only 15-32% on complex workflows -- indicates fundamental architectural limitations in memory management, hierarchical planning, and state coordination rather than incremental capability gaps addressable through better training or prompting. UI-CUBE functions as an enterprise-readiness diagnostic, revealing that while current CUAs can manipulate individual interface elements, they cannot yet function as reliable workflow automation tools. These findings provide architectural insights essential for developing production-ready CUAs capable of managing complex, multi-step enterprise processes.

cs.SE↗

arXiv2025

When Embedding Models Meet: Procrustes Bounds and Applications

Embedding models trained separately on similar data often produce representations that encode stable information but are not directly interchangeable. This lack of interoperability raises challenges in several practical applications, such as model retraining, partial model upgrades, and multimodal search. Driven by these challenges, we study when two sets of embeddings can be aligned by an orthogonal transformation. We show that if pairwise dot products are approximately preserved, then there exists an isometry that closely aligns the two sets, and we provide a tight bound on the alignment error. This insight yields a simple alignment recipe, Procrustes post-processing, that makes two embedding models interoperable while preserving the geometry of each embedding space. Empirically, we demonstrate its effectiveness in three applications: maintaining compatibility across retrainings, combining different models for text retrieval, and improving mixed-modality search, where it achieves state-of-the-art performance.

cs.LG↗

arXiv1999

Simulations of Nonthermal Electron Transport in Multidimensional Flows: Synthetic Observations of Radio Galaxies

We have applied an effective numerical scheme for cosmic-ray transport to 3D MHD simulations of jet flow in radio galaxies (see the companion paper by Jones et al. 1999). The marriage of relativistic particle and 3D magnetic field information allows us to construct a rich set of ``synthetic observations'' of our simulated objects. The information is sufficient to calculate the ``true'' synchrotron emissivity at a given frequency using explicit information about the relativistic electrons. This enables us to produce synchrotron surface-brightness maps, including polarization. Inverse-Compton X-ray surface-brightness maps may also be produced. First results intended to explore the connection between jet dynamics and electron transport in radio lobes are discussed. We infer lobe magnetic field values by comparison of synthetically observed X-ray and synchrotron fluxes, and find these ``inverse-Compton'' fields to be quite consistent with the actual RMS field averaged over the lobe. The simplest minimum energy calculation from the synthetic observations also seems to agree with the actual simulated source properties.

astro-ph↗