Prépublication
· 2026 arXiv
EN
Current evaluation of LLM-generated debate largely focuses on argumentative quality, leaving the value structure of generated arguments underexamined. We introduce a diagnostic metric framework for comparing how values are expressed and organized in human-refe...
Maoyuan Li, Haoyuan Li et al.
#cs.AI
Prépublication
· 2026 arXiv
EN
TS2Vec is one of the strongest self-supervised methods for time series classification, introduced in 2022. It is designed to be trained anew on every dataset: self-supervised pre-training followed by linear probing. Since then, the field has shifted towards fo...
Vasilii Feofanov, Zhenghan Tai et al.
#cs.LG
Prépublication
· 2026 arXiv
EN
Computer-use agents are limited by the interfaces humans give them. An agent may type a spreadsheet cell by cell when a single line of code would do, or print all two thousand lines of a file through a shell to find one function. Both the interfaces and the kn...
Saaket Agashe, Yuzhe Yang et al.
#cs.AI
Prépublication
· 2026 arXiv
EN
RTL repair benchmarks should measure whether a model can fix broken RTL given a specification. To this end, we construct and hash-bind RTLRepairDataset, 5,784 (broken, fixed) training pairs; RTLRepairBench, 459 held-out cases with 374 syntactic and 85 behavior...
Yeyin Eva Zhu, Rishabh Ranawat
#cs.AI
Prépublication
· 2026 arXiv
EN
Agentic on-policy distillation (OPD) trains a student agent on its own trajectories while a teacher scores every token. A natural explanation of where it goes wrong is compounding error: the student's mistakes carry its trajectories beyond the region where the...
Shu Zhao, Tan Yu
#cs.CL
Prépublication
· 2026 arXiv
EN
Simulation is a powerful tool for robotics, but building diverse, simulation-ready scenes at scale remains difficult. Reconstructing scenes from single images is a promising alternative, but visual similarity alone is insufficient: objects must also be recover...
Rundong Luo, Yunong Liu et al.
#cs.RO
Prépublication
· 2026 arXiv
EN
We derive explicit expressions for the primordial scalar and tensor spectra at arbitrary finite order $p$ in the slow-roll expansion, valid both for canonical single-field inflation and $k$-inflation. At any order, the spectra are determined by known combinati...
William Giarè
#astro-ph.CO
Prépublication
· 2026 arXiv
EN
Solar energetic particle (SEP) events threaten space infrastructure, yet physics-based prediction models depend on numerous poorly constrained free parameters. We introduce the Fujitsu Solar Energetic particle Intelligent Tuning and Evaluation Network (SEITEN)...
Hiroyuki Tako Ishikawa, Naho Fujita et al.
#astro-ph.SR
Prépublication
· 2026 arXiv
EN
Small planets transiting the nearest M dwarfs are the terrestrial planets most accessible to detailed characterisation. We report a sub-Earth-sized transiting planet candidate in the wide (17.6") M-dwarf binary GJ 774 at 12.86 pc, most likely orbiting the M2.5...
Jaden Tripp
#astro-ph.EP
Prépublication
· 2026 arXiv
EN
Hot Jupiters are typically thought to be "lonely", but a small and growing subset of them have been found to have nearby planets in the same system. We present the discovery of a new member of this class of systems, TOI-3686. TOI-3686 c is a hot Jupiter with $...
Samuel W. Yee, Tarisai Dziire et al.
#astro-ph.EP
Prépublication
· 2026 arXiv
EN
We first derived the formulae of recursive reduction and dlog-form differential equations for arbitrary tree-level cosmological correlator, taking the external relations of massless bulk propagators into consideration. The differential equations could be syste...
Jiaqi Chen, Yi-Xiao Tao et al.
#hep-ph
Prépublication
· 2026 arXiv
EN
The TESS mission is designed to survey the entire sky to find planets most amenable to follow-up observations, and transit searches have therefore focused specifically on bright targets. Faint stars ($T_{mag}>13.5$) have not been systematically searched for pl...
Matthew Lastovka, Thomas Barclay et al.
#astro-ph.EP