Policy Compiler for Secure Agentic Systems
arXiv:2602.16708v2 Announce Type: replace-cross Abstract: LLM-based agents are increasingly being deployed in contexts requiring complex authorization policies: customer service protocols,…
Towards Cross-lingual Values Assessment: A Consensus-Pluralism Perspective
arXiv:2602.17283v1 Announce Type: cross Abstract: While large language models (LLMs) have become pivotal to content safety, current evaluation paradigms primarily…
Federated Latent Space Alignment for Multi-user Semantic Communications
arXiv:2602.17271v1 Announce Type: cross Abstract: Semantic communication aims to convey meaning for effective task execution, but differing latent representations in…
RoboGene: Boosting VLA Pre-training via Diversity-Driven Agentic Framework for Real-World Task Generation
arXiv:2602.16444v2 Announce Type: replace-cross Abstract: The pursuit of general-purpose robotic manipulation is hindered by the scarcity of diverse, real-world interaction…
Preconditioned inexact stochastic ADMM for deep models
Nature Machine Intelligence, Published online: 20 February 2026; doi:10.1038/s42256-026-01182-3 Zhou et al. develop PISA, an optimizer for deep learning models…
FlowPrefill: Decoupling Preemption from Prefill Scheduling Granularity to Mitigate Head-of-Line Blocking in LLM Serving
arXiv:2602.16603v1 Announce Type: cross Abstract: The growing demand for large language models (LLMs) requires serving systems to handle many concurrent…