Security
Cybersecurity is the rickety scaffolding supporting everything you do online. For every new feature or app, there are a thousand different ways it can break – and a hundred of those can be exploited by criminals for data breaches, identity...
Audio
From streaming music and audiobooks to live audio rooms and podcasts, every major player in tech is trying to own a chunk of the listening experience. Spotify is expanding beyond music streaming, YouTube is becoming an audio-only destination, and Apple...
Film
Cinema isn’t just about the latest Disney/Pixar project or Star Wars spin-off. Memorable storytelling is happening all over the film industry, from Hollywood’s box-office-busting superhero smashes to small, innovative indie experiments. The Verge’s film section is here to help you...
AI
Artificial intelligence is more a part of our lives than ever before. While some might call it hype and compare it to NFTs or 3D TVs, AI is causing a sea change in nearly every part of the technology industry....
Creators
YouTube, Instagram, SoundCloud, and other online platforms are changing the way people create and consume media. The Verge’s Creators section covers the people using these platforms, what they’re making, and how those platforms are changing (for better and worse) in...
Space
Verge Science is here to bring you the most up-to-date space news and analysis, whether it’s about the latest findings from NASA or comprehensive coverage of the next SpaceX rocket launch to the International Space Station. We’ll take you inside...
Health
The Verge is about technology and how it makes us feel. Founded in 2011, we offer our audience everything from breaking news to reviews to award-winning features and investigations, on our site, in video, and in podcasts.
Scaling the Scaling Logic: Agentic Meta-Synthesis of Logic Reasoning
arXiv:2602.13218v1 Announce Type: new Abstract: Scaling verifiable training signals remains a key bottleneck for Reinforcement Learning from Verifiable Rewards (RLVR). Logical reasoning is a natural substrate: constraints are formal and answers are programmatically checkable. However, prior synthesis pipelines either depend...
Lang2Act: Fine-Grained Visual Reasoning through Self-Emergent Linguistic Toolchains
arXiv:2602.13235v1 Announce Type: new Abstract: Visual Retrieval-Augmented Generation (VRAG) enhances Vision-Language Models (VLMs) by incorporating external visual documents to address a given query. Existing VRAG frameworks usually depend on rigid, pre-defined external tools to extend the perceptual capabilities of VLMs,...
General learned delegation by clones
arXiv:2602.13262v1 Announce Type: new Abstract: Frontier language models improve with additional test-time computation, but serial reasoning or uncoordinated parallel sampling can be compute-inefficient under fixed inference budgets. We propose SELFCEST, which equips a base model with the ability to spawn...
Human-Centered Explainable AI for Security Enhancement: A Deep Intrusion Detection Framework
arXiv:2602.13271v1 Announce Type: new Abstract: The increasing complexity and frequency of cyber-threats demand intrusion detection systems (IDS) that are not only accurate but also interpretable. This paper presented a novel IDS framework that integrated Explainable Artificial Intelligence (XAI) to enhance...
BEAGLE: Behavior-Enforced Agent for Grounded Learner Emulation
arXiv:2602.13280v1 Announce Type: new Abstract: Simulating student learning behaviors in open-ended problem-solving environments holds potential for education research, from training adaptive tutoring systems to stress-testing pedagogical interventions. However, collecting authentic data is challenging due to privacy concerns and the high...
Mirror: A Multi-Agent System for AI-Assisted Ethics Review
arXiv:2602.13292v1 Announce Type: new Abstract: Ethics review is a foundational mechanism of modern research governance, yet contemporary systems face increasing strain as ethical risks arise as structural consequences of large-scale, interdisciplinary scientific practice. The demand for consistent and defensible decisions...
Detecting Jailbreak Attempts in Clinical Training LLMs Through Automated Linguistic Feature Extraction
arXiv:2602.13321v1 Announce Type: new Abstract: Detecting jailbreak attempts in clinical training large language models (LLMs) requires accurate modeling of linguistic deviations that signal unsafe or off-task user behavior. Prior work on the 2-Sigma clinical simulation platform showed that manually annotated...
OMNI-LEAK: Orchestrator Multi-Agent Network Induced Data Leakage
arXiv:2602.13477v1 Announce Type: new Abstract: As Large Language Model (LLM) agents become more capable, their coordinated use in the form of multi-agent systems is anticipated to emerge as a practical paradigm. Prior work has examined the safety and misuse risks...
A First Proof Sprint
arXiv:2602.13587v1 Announce Type: new Abstract: This monograph reports a multi-agent proof sprint on ten research-level problems, combining rapid draft generation with adversarial verification, targeted repair, and explicit provenance. The workflow uses wiring-diagram decompositions of claim dependencies to localize gaps and...
The acquisition of English irregular inflections by Yemeni L1 Arabic learners: A Universal Grammar approach
arXiv:2602.13816v1 Announce Type: new Abstract: This study examines the acquisition of English irregular inflections by Yemeni learners of English as a second language (L2), utilizing a Universal Grammar (UG) approach. Within the UG approach, the study considers Feature Reassembly Hypothesis...
Geometry-Preserving Aggregation for Mixture-of-Experts Embedding Models
arXiv:2602.14039v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) embedding models combine expert outputs using weighted linear summation, implicitly assuming a linear subspace structure in the embedding space. This assumption is shown to be inconsistent with the geometry of expert representations. Geometric...
Mind the Boundary: Stabilizing Gemini Enterprise A2A via a Cloud Run Hub Across Projects and Accounts
arXiv:2602.17675v1 Announce Type: cross Abstract: Enterprise conversational UIs increasingly need to orchestrate heterogeneous backend agents and tools across project and account boundaries in a secure and reproducible way. Starting from Gemini Enterprise Agent-to-Agent (A2A) invocation, we implement an A2A Hub...
Curriculum Learning for Efficient Chain-of-Thought Distillation via Structure-Aware Masking and GRPO
arXiv:2602.17686v1 Announce Type: cross Abstract: Distilling Chain-of-Thought (CoT) reasoning from large language models into compact student models presents a fundamental challenge: teacher rationales are often too verbose for smaller models to faithfully reproduce. Existing approaches either compress reasoning into single-step,...
MIDAS: Mosaic Input-Specific Differentiable Architecture Search
arXiv:2602.17700v1 Announce Type: cross Abstract: Differentiable Neural Architecture Search (NAS) provides efficient, gradient-based methods for automatically designing neural networks, yet its adoption remains limited in practice. We present MIDAS, a novel approach that modernizes DARTS by replacing static architecture parameters...
Early Evidence of Vibe-Proving with Consumer LLMs: A Case Study on Spectral Region Characterization with ChatGPT-5.2 (Thinking)
arXiv:2602.18918v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly used as scientific copilots, but evidence on their role in research-level mathematics remains limited, especially for workflows accessible to individual researchers. We present early evidence for vibe-proving with a...
Robust and Efficient Tool Orchestration via Layered Execution Structures with Reflective Correction
arXiv:2602.18968v1 Announce Type: new Abstract: Tool invocation is a core capability of agentic systems, yet failures often arise not from individual tool calls but from how multiple tools are organized and executed together. Existing approaches tightly couple tool execution with...
Quantifying Automation Risk in High-Automation AI Systems: A Bayesian Framework for Failure Propagation and Optimal Oversight
arXiv:2602.18986v1 Announce Type: new Abstract: Organizations across finance, healthcare, transportation, content moderation, and critical infrastructure are rapidly deploying highly automated AI systems, yet they lack principled methods to quantify how increasing automation amplifies harm when failures occur. We propose a...
Asking the Right Questions: Improving Reasoning with Generated Stepping Stones
arXiv:2602.19069v1 Announce Type: new Abstract: Recent years have witnessed tremendous progress in enabling LLMs to solve complex reasoning tasks such as math and coding. As we start to apply LLMs to harder tasks that they may not be able to...
Beyond Behavioural Trade-Offs: Mechanistic Tracing of Pain-Pleasure Decisions in an LLM
arXiv:2602.19159v1 Announce Type: new Abstract: Prior behavioural work suggests that some LLMs alter choices when options are framed as causing pain or pleasure, and that such deviations can scale with stated intensity. To bridge behavioural evidence (what the model does)...
Automated Generation of Microfluidic Netlists using Large Language Models
arXiv:2602.19297v1 Announce Type: new Abstract: Microfluidic devices have emerged as powerful tools in various laboratory applications, but the complexity of their design limits accessibility for many practitioners. While progress has been made in microfluidic design automation (MFDA), a practical and...
Artificial Intelligence for Modeling & Simulation in Digital Twins
arXiv:2602.19390v1 Announce Type: new Abstract: The convergence of modeling & simulation (M&S) and artificial intelligence (AI) is leaving its marks on advanced digital technology. Pertinent examples are digital twins (DTs) - high-fidelity, live representations of physical assets, and frequent enablers...
IR$^3$: Contrastive Inverse Reinforcement Learning for Interpretable Detection and Mitigation of Reward Hacking
arXiv:2602.19416v1 Announce Type: new Abstract: Reinforcement Learning from Human Feedback (RLHF) enables powerful LLM alignment but can introduce reward hacking - models exploit spurious correlations in proxy rewards without genuine alignment. Compounding this, the objectives internalized during RLHF remain opaque,...
Asymptotic Semantic Collapse in Hierarchical Optimization
arXiv:2602.18450v1 Announce Type: new Abstract: Multi-agent language systems can exhibit a failure mode where a shared dominant context progressively absorbs individual semantics, yielding near-uniform behavior across agents. We study this effect under the name Asymptotic Semantic Collapse in Hierarchical Optimization....