Prépublication
· 2026 arXiv
EN
In this work, we survey M-type stars within 15 pc observed by Gaia based on their colour, magnitude, and quality of astrometric data. We aim to detect new substellar companions using primarily Gaia astrometry and, when available, proper-motion anomaly (PMa) al...
F. Destriez, A. -M. Lagrange et al.
#astro-ph.EP
Prépublication
· 2026 arXiv
EN
The over $5σ$ Hubble tension continues to motivate modifications of the standard $Λ$-cold-dark-matter ($Λ\rm CDM$) model. The large number of proposed resolutions for the Hubble tension, broadly divided into early- and late-time solutions, motivates phenomenol...
Jia-Le Ling, Shao-Jiang Wang
#astro-ph.CO
Prépublication
· 2026 arXiv
EN
Test-time scaling has emerged as a key inference strategy for reasoning models, where a model generates a large number of candidate solutions in the hope of finding at least one correct solution. Running all candidate solutions to completion can be computation...
Mahdi Salmani, Adel Javanmard et al.
#cs.AI
Prépublication
· 2026 arXiv
EN
Wrong automatic routing of an IT support ticket can cost more than human triage. We evaluate cost-aware abstention as an offline, cost-conditional readiness assessment: select a routing policy on calibration data under explicit costs, then evaluate that frozen...
Sachin Gupta
#cs.LG
Prépublication
· 2026 arXiv
EN
Meta-reinforcement learning aims to train agents that adapt quickly to unseen tasks from limited interaction, but this requires representing task evidence over long interaction histories. Classical recurrent agents compress experience into hidden states, while...
Ali Najar, Hosein Hasani et al.
#cs.LG
Prépublication
· 2026 arXiv
EN
Tool-using language model agents rely on environmental facts to decide whether an action is permitted. When a tool response omits a safety-relevant fact, an agent may carry out a prohibited action even though the user request is benign and every returned state...
Qijin Zhang, Hanzhen Wang et al.
#cs.AI
Prépublication
· 2026 arXiv
EN
Many recent open-weight language models use n-gram embedding tables to improve performance. These tables store learned representations of short token sequences, such as pairs or triples of consecutive tokens, which the model retrieves during processing. Howeve...
Stephen Chung, Wenyu Du
#cs.CL
Prépublication
· 2026 arXiv
EN
Chain-of-thought (CoT) prompting elicits step-by-step rationales that appear to explain model predictions, but there is no guarantee these steps causally drive the final answer. In standard autoregressive generation, dense attention allows each reasoning step...
Gabriele Dominici, Teague McMillan et al.
#cs.LG
Prépublication
· 2026 arXiv
EN
Multilingual pipelines such as FineWeb2 apply one recipe across a thousand languages, leaving the failure modes of individual languages unanticipated. We use an LLM once, as a corpus debugger rather than a classifier: a tool-using agent explores the corpus thr...
Marek Šuppa, Ivan Vykopal et al.
#cs.CL
Prépublication
· 2026 arXiv
EN
Instrumental convergence is often invoked as a general reason to expect capable agents to acquire or express power-seeking subgoals: self-preservation, resource acquisition, deception, or resistance to oversight which poses an important threat to the society....
Barış Alparslan, Sandy Tanwisuth et al.
#cs.LG
Prépublication
· 2026 arXiv
EN
While monolingual language model (LM) surprisal is widely established as a predictor of reading times, it cannot capture the non-native (L2) reading dynamics that are shaped by the reader's first language (L1). In this work, we investigate whether the cross-li...
Abderrahmane Issam, Irene E. Winther et al.
#cs.CL
Prépublication
· 2026 arXiv
EN
Purpose: To describe an evidence-aware retrieval evaluation protocol for a clinical retrieval-augmented generation (RAG) system over breast lesion management literature, addressing the dependence of retrieval scores on annotation coverage. Methods: An 18-docum...
Miguel Mochizuki Silva, Samuel Ismael et al.
#cs.CL