Prépublication
· 2026 arXiv
EN
Reinforcement learning enables mobile robots to make fast and scalable navigation decisions in constrained human-shared environments. However, directly extending single-robot approaches to multi-robot settings often fails to ensure safety and efficiency, espec...
Zehao Wang, Jianpeng Yao et al.
#cs.RO
Prépublication
· 2026 arXiv
EN
In this paper, we systematically investigate the mechanisms, scaling behavior, and generalization of physical Recursive self-improvement. We introduce PhysRSI-eval to quantify physical RSI through a five-axis metric: First-Attempt Performance, Efficiency, Succ...
Zekai Li, Jiayi Yu et al.
#cs.RO
Prépublication
· 2026 arXiv
EN
The goal of a world model is to capture the dynamics of an environment. This has the great appeal that it allows agents to plan and simulate a course of actions with the help of a world model. For these uses to be reliable, however, the learned dynamics must b...
Heejeong Nam, Divyat Mahajan et al.
#cs.AI
Prépublication
· 2026 arXiv
EN
Systems that combine several large language models (LLMs) often use one context for many questions. When the context is passed between models as text, the receiving model processes all of its tokens again for every question. Avoiding this cost requires a conte...
Huawei Lin, Jinting Liu et al.
#cs.CL
Prépublication
· 2026 arXiv
EN
LLM agents that compute the right answer can still answer wrongly. Agent harnesses increasingly keep long tool outputs out of the context window, saving them to files that the agent searches or reads on demand. We ask where this costs accuracy with a real scie...
Ke Zhang, Sahchit Chundur et al.
#cs.AI
Prépublication
· 2026 arXiv
EN
Many modern language models have adopted hybrid architectures that incorporate both linear-time recurrence and softmax attention. Modern recurrence layers provide a highly expressive mixing mechanism while ensuring high throughput by compressing contextual inf...
Xingyu Shen, Yingfa Chen et al.
#cs.CL
Prépublication
· 2026 arXiv
EN
Agent learning is shifting from learning from human data toward learning through interaction with the world. However, scaling such learning directly in real-world computer systems is challenging and can introduce substantial security risks. We therefore propos...
Zhaoyang Wang, Qianhui Wu et al.
#cs.AI
Prépublication
· 2026 arXiv
EN
We present an updated analysis of non-standard neutrino self-interactions, where the interaction is effectively mediated by a heavy particle, using the latest available data from DESI and the CMB. The considered data include combinations of DESI DR1 full-shape...
Hernán E. Noriega, Josue De-Santiago et al.
#astro-ph.CO
Texte transcrit
· 1834 Wikisource
FR
Extrait : Louis-François-Hilarion Audibert Histoire et roman Histoire et roman , Dufey, Libraire, 1834. Texte sur une seule page (ne fait pas partie de l’ouvrage
Wikisource
#Histoire
Texte transcrit
· 1860 Wikisource
FR
Extrait : Ammien Marcellin Histoire de Rome traduction sous la direction de M. Nisard, Paris Firmin Didot, 1860 Les treize premiers livres manquent. Livre XIV Livre
Wikisource
#Histoire
Texte transcrit
· 1913 Wikisource
FR
Extrait : Lavisse Histoire de France — Cours élémentaire Armand Colin, 1913. Texte sur une seule page ERNEST LAVISSE DE L’ACADÉMIE FRANÇAISE HISTOIRE DE FRANCE
Wikisource
#Histoire
Prépublication
· 2026 arXiv
EN
Earth system models underpin the evidence that informs net-zero policy, yet their energy demands are rarely considered when judging model quality. Using archived output from 159 models spanning five generations of the Coupled Model Intercomparison Project (CMI...
Ioana Colfescu, Annalisa Bracco et al.
#physics.ao-ph