Prépublication
· 2026 arXiv
EN
Reusable skills let LLM agents load task-specific instructions on demand, but they make execution depend on implicit routing over skill metadata. We test whether this design scales by holding SkillsBench tasks and their golden skills fixed while adding irrelev...
Jinlin Liu, Wei Chen et al.
#cs.AI
Prépublication
· 2026 arXiv
EN
Large language models (LLMs) increasingly act as personal assistants; however, little is known about how they capture national-level preferences on a global scale. Given that "time" is a universal and representative concept, we examine LLMs' time preferences b...
Yifan He, Sofie Goethals et al.
#cs.CY
Prépublication
· 2026 arXiv
EN
Terminal agents have shown strong abilities in complex coding tasks. However, they often struggle to recover from errors during long-running execution (e.g., command errors, faulty implementations), eventually leading to task failures. To this end, we present...
Wei Xie, Kaituo Feng et al.
#cs.AI
Prépublication
· 2026 arXiv
EN
Large vision-language models (LVLMs) have shown strong potential for embodied vision-language navigation (VLN), yet their performance degrades on long-horizon trajectories due to context-length limits, redundant historical observations, and unstable spatial al...
Xueyao Wei, Yifei Wang et al.
#cs.RO
Prépublication
· 2026 arXiv
EN
The Hybrid forecast covariance model is an operationally successful way to build a background error covariance matrix. It is constructed as a weighted sum, with scalar weights, of the climatological covariance matrix and a localized ensemble covariance matrix,...
Francesco Sardelli, Craig H. Bishop
#physics.ao-ph
Prépublication
· 2026 arXiv
EN
Many approaches have recently been proposed to combine data assimilation with machine learning for improved forecasts with geophysical models. Here, we focus on combining advanced sequential data assimilation schemes with a generative forecasting model which a...
Marc Bocquet, Tobias S. Finn et al.
#stat.ML
Prépublication
· 2026 arXiv
EN
Global reanalyses are too coarse to resolve the convective systems that produce most West African monsoon rainfall. In this work, we use U-Net based architectures to downscale daily ERA5 fields (0.25°) to IMERG V07 satellite precipitation (0.1°) over West Afri...
David Sagna, Redouane Lguensat et al.
#physics.ao-ph
Texte transcrit
Wikisource
FR
Extrait : rendit ensuite à Padoue : il y cultiva principalement l’anatomie et la botanique. Thomas Bartholin lui attribue la découverte du canal pancréatique. Hoffmann
Wikisource
#Botanique
Prépublication
· 2026 arXiv
EN
Interpreting machine learning model predictions is a central challenge, particularly for black-box vision models. Concept-based attribution methods interpret models using human-understandable concepts. Existing concept-based methods can only interpret classifi...
Bhanu Tokas, Rahul Nair et al.
#cs.CV
Prépublication
· 2026 arXiv
EN
Neural semantic parsers generate meaning representations token by token, yet well-formedness depends on references, scope, and graph relations that unfold during generation. Constrained decoding prevents locally invalid tokens but does not guarantee that a val...
Xiao Zhang
#cs.CL
Prépublication
· 2026 arXiv
EN
As AI agents increasingly rely on external tools, accurate retrieval is essential for reliable behavior. Existing methods optimize semantic relevance but largely ignore tool availability during execution. To address this gap, we propose RATED (Reliability-Awar...
Weiliang Chen, Song Liao
#cs.AI
Prépublication
· 2026 arXiv
EN
Personal agents increasingly connect to services across the web and applications by using tools. As the effects of their actions accumulate and interact across services, unintended or harmful outcomes can arise when agents fulfill benign user requests. Proacti...
Yeonsung Jung, Zhiyuan Wang et al.
#cs.AI