AI News Archive: May 19, 2026 — Part 26

Sourced from 500+ daily AI sources, scored by relevance.

• TombWriter: Scaffolding Story Archeology through Beat-Level Interaction in Human-AI Co-Writing

  The dominant paradigm for LLM interaction in AI co-writing uses disposable prompts that vanish after use. This may lead to imprecise results, cumbersome workflows, and diminished author agency and ownership. We propose LLM-based story archeology, where prompts serve as a hierarchical story instrumen...

  📄 ResearchMay 19, 2026http://arxiv.org/abs/2605.19681v1
• The Accessibility Capability Boundary: Operational Limits and Expansion Potential of AI-Generated Browser-Native Accessibility Systems

  As large language models (LLMs) demonstrate increasing competence in synthesizing functional user interfaces, a fundamental question emerges in accessibility computing: \textit{how far can AI-driven accessibility systems go?} This paper introduces the \textit{Accessibility Capability Boundary} (ACB)...

  📄 ResearchMay 19, 2026http://arxiv.org/abs/2605.19638v1
• Toward User Comprehension Supports for LLM Agent Skill Specifications

  Users often interpret and select agent skills through their \texttt{SKILL.md} specifications. To protect users, existing audits mainly focus on malicious or unsafe skills. We study the complementary question of whether specifications help users form bounded expectations about what a skill consumes, ...

  📄 ResearchMay 19, 2026http://arxiv.org/abs/2605.19362v1
• From Role to Person: Trust Calibration Challenges in Twin Agents

  Agentic AI has taken on the role of assistant, collaborator, and decision-support tool. We argue the next role on that list is more personal: you. These are digital twins of each individual -- twin agents -- representing their knowledge, perspective, and communicative style to colleagues when they a...

  📄 ResearchMay 19, 2026http://arxiv.org/abs/2605.19838v1
• Material for Thought: Generative AI as an Active Creative Medium

  Human-AI collaboration research has largely positioned the human as a judge of AI output, centering effort on evaluating whether rec- ommendations are reliable enough to accept. This decision-support framing leaves little room for the human as creator. We argue that for creative work, this framing m...

  📄 ResearchMay 19, 2026http://arxiv.org/abs/2605.19832v1
• CutVerse: A Compositional GUI Agents Benchmark for Media Post-Production Editing

  While GUI agents have made significant progress in web navigation and basic operating system tasks, their capabilities in professional creative workflows remain largely underexplored. To bridge this gap, we introduce Cutverse, a benchmark designed to systematically evaluate autonomous GUI agents in ...

  📄 ResearchMay 19, 2026http://arxiv.org/abs/2605.19484v1
• Platform architecture determines whether recommendation algorithms can shape information quality on social media

  Social media platforms shape public discourse through two fundamental design choices that naturally co-occur in any field investigation: platform architecture, which defines what types of actors exist and how they interact, and recommendation algorithm, which determines what content is surfaced to u...

  📄 ResearchMay 19, 2026http://arxiv.org/abs/2605.19204v1
• BiRD: A Bidirectional Ranking Defense Mechanism for Retrieval Augmented Generation

  The growing adoption of Retrieval-Augmented Generation (RAG) has led to a rise in adversarial attacks. Existing defenses, relying on semantic analysis or voting, face a trade-off between high computational cost and limited robustness under strong poisoning attacks. Their fundamental limitation is th...

  📄 ResearchMay 19, 2026http://arxiv.org/abs/2605.20123v1
• Awakening the Hydra: Stabilizing Multi-Concept Backdoor Injection in Text-to-Image Diffusion Models

  Text-to-image diffusion models are increasingly developed through open-source reuse and repeated downstream fine-tuning, where reused checkpoints are difficult to verify and thus more susceptible to hidden backdoor behaviors. In such ecosystems, a single pretrained model may be sequentially adapted ...

  📄 ResearchMay 19, 2026http://arxiv.org/abs/2605.19698v1
• Exposing Functional Fusion: A New Class of Strategic Backdoor in Dynamic Prompt Architectures

  Existing ViT backdoor attacks based on backbone-overwriting full-tuning are computationally expensive and inflict performance degradation. This has forced adversaries towards the Visual Parameter-Efficient Fine-Tuning (PEFT) paradigm, dominated by adapter-based (e.g., LoRA) and prompt-based (e.g., V...

  📄 ResearchMay 19, 2026http://arxiv.org/abs/2605.19478v1
• XAI FL-IDS: A Federated Learning and SHAP-Based Explainable Framework for Distributed Intrusion Detection Systems

  An Intrusion Detection System (IDS) is vital in cybersecurity, detecting unauthorized activity across networks. With attacks on network layers increasing, stronger IDSs are needed. Yet most IDSs rely on centralized detection, forcing IoT nodes to ship data to a server, adding overhead and offering n...

  📄 ResearchMay 19, 2026http://arxiv.org/abs/2605.19448v1
• Exploring and Developing a Pre-Model Safeguard with Draft Models

  Large Language Model (LLM) alignment remains vulnerable to jailbreak attacks that elicit unsafe responses, motivating pre-model and post-model guards. Pre-model guards audit the safety of prompts before invoking target models. However, relying solely on the prompt often leads to high false-negative ...

  📄 ResearchMay 19, 2026http://arxiv.org/abs/2605.19321v1
• Backdooring Masked Diffusion Language Models

  Masked diffusion language models (MDLMs) are emerging as a compelling new paradigm for text generation, but their training-time security remains largely unexplored. Existing backdoor attacks on Gaussian diffusion models or autoregressive language models do not directly apply to MDLMs because MDLMs r...

  📄 ResearchMay 19, 2026http://arxiv.org/abs/2605.19262v1
• Detecting and Mitigating Backdoor Attacks in OTA-FL Systems: A Two-Stage Robust Aggregation Scheme

  Over-the-air federated learning (OTA-FL) improves communication efficiency by exploiting the superposition property of wireless channels, but this same property also creates a critical security vulnerability: the parameter server (PS) cannot access individual local updates, making it difficult to id...

  📄 ResearchMay 19, 2026http://arxiv.org/abs/2605.19253v1
• Quantum Machine Learning for Cyber-Physical Anomaly Detection in Unmanned Aerial Vehicles: A Leakage-Free Evaluation with Proxy-Audited Feature Sets

  Unmanned aerial vehicles (UAVs) are cyber-physical systems whose attack surface spans networked avionics and on-board sensor fusion: a compromised GPS or battery module can mimic a benign mission segment and evade naive anomaly detectors. We present a leakage-free evaluation of quantum machine learn...

  📄 ResearchMay 19, 2026http://arxiv.org/abs/2605.19233v1
• Token by Token, Compromised: Backdoor Vulnerabilities in Unified Autoregressive Models

  Unified autoregressive models (UAMs) are transformer models that generate text as well as image tokens within a single autoregressive pass. Shared parameters and a multimodal vocabulary simplify the training pipeline and facilitate flexible multimodal generation, yet might introduce new vulnerabilit...

  📄 ResearchMay 19, 2026http://arxiv.org/abs/2605.19227v1
• Hunting Vulnerability Variants in AI Infra: Measurement and Reference-Driven Detection

  AI infra has become a shared execution layer for model training, deployment, and agent orchestration. Because many projects reimplement similar model-centric workflows, a vulnerability disclosed in one repository can recur as a variant in another repository with a related design. Yet the prevalence ...

  📄 ResearchMay 19, 2026http://arxiv.org/abs/2605.20051v1
• DASM: Domain-Aware Sharpness Minimization for Multi-Domain Voice Stream Steganalysis

  The growing use of information hiding in network streaming media for covert communication poses a significant security threat, necessitating the development of robust detection technologies. However, existing steganalysis methods for network voice streams mostly rely on data distributions in specifi...

  📄 ResearchMay 19, 2026http://arxiv.org/abs/2605.19955v1
• Measuring Safety Alignment Effects in Autonomous Security Agents

  Do stock safety-aligned language models and their uncensored or abliterated derivatives behave differently when run as autonomous security agents? Single-turn refusal benchmarks cannot answer this question: security agents must inspect repositories, call tools, and produce vulnerability evidence ins...

  📄 ResearchMay 19, 2026http://arxiv.org/abs/2605.19722v1
• SCARA: A Semantics-Constrained Autonomous Remediation Agent for Opaque Industrial Software Vulnerabilities

  Critical-infrastructure operators are increasingly expected to assess and remediate vulnerabilities in deployed industrial software. However, much of this software exists as opaque industrial software (OIS), including stripped firmware, proprietary protocol handlers, and compiled control logic witho...

  📄 ResearchMay 19, 2026http://arxiv.org/abs/2605.19668v1
• Inferring Sensitive Attributes from Knowledge Graph Embeddings: Attack and Defense Strategies

  Knowledge Graphs (KGs) are a powerful representation of linked data, offering flexibility, semantic richness, and support for knowledge enrichment and reasoning. They help data owners organize and exploit heterogeneous data to provide insightful services (e.g., recommendations), yet real-world KGs a...

  📄 ResearchMay 19, 2026http://arxiv.org/abs/2605.19644v1
• Devilray: A Systematic Adversarial Model Revealing Blind Spots in Fake Base Station Detection

  Fake Base Station (FBS) detection has been a critical focus of cellular security research for over two decades. However, significant financial and regulatory barriers to accessing commercial FBS (C-FBS) devices have limited direct visibility into real-world operations, forcing detection systems to b...

  📄 ResearchMay 19, 2026http://arxiv.org/abs/2605.19232v1
• Can LLMs Produce Better Object-Oriented Designs than Human-Involved Development?

  Background: Large Language Models (LLMs) are increasingly used for code generation. However, their ability to generate multi-class projects that require object-oriented design (OOD) remains unclear, especially relative to projects developed with human involvement. Aims: The primary objective of this...

  📄 ResearchMay 19, 2026http://arxiv.org/abs/2605.19901v1
• Prior Knowledge or Search? A Study of LLM Agents in Hardware-Aware Code Optimization

  LLM discovery and optimization systems are increasingly applied across domains, implementing a common propose-evaluate-revise loop. Such optimization or discovery progresses via context conditioning on received feedback from an environment. However, as modern LLM agents are increasingly complex in t...

  📄 ResearchMay 19, 2026http://arxiv.org/abs/2605.19782v1
• CriterAlign: Criterion-Centric Rationale Alignment for Code Preference Judging

  Pairwise human preference prediction is central to evaluating code-generation systems, where quality often depends on task-specific trade-offs beyond functional correctness. While rubric-based LLM judges improve interpretability by decomposing evaluation into explicit criteria, most existing pipelin...

  📄 ResearchMay 19, 2026http://arxiv.org/abs/2605.19665v1
• Characterizing Real-World Bugs in Tile Programs for Automated Bug Detection

  Tile-based programming frameworks are increasingly adopted to write high-performance GPU kernels in domains such as deep learning and scientific computing. While these frameworks enhance productivity and hardware utilization, their multi-stage compilation pipelines introduce distinct code generation...

  📄 ResearchMay 19, 2026http://arxiv.org/abs/2605.19652v1
• Provable Fairness Repair for Deep Neural Networks

  Deep neural networks (DNNs) are suffering from ethical issues such as individual discrimination. In response, extensive NN repair techniques have been developed to adjust models and mitigate such undesired behaviors. However, existing fairness repair methods are typically data-centric, which often l...

  📄 ResearchMay 19, 2026http://arxiv.org/abs/2605.19549v1
• MOCHA: Multi-Objective Chebyshev Annealing for Agent Skill Optimization

  LLM agents organize behavior through skills - structured natural-language specifications governing how an agent reasons, retrieves, and responds. Unlike monolithic prompts, skills are multi-field artifacts subject to hard platform constraints: description fields are truncated for routing, instructio...

  📄 ResearchMay 19, 2026http://arxiv.org/abs/2605.19330v1
• Does Code Cleanliness Affect Coding Agents? A Controlled Minimal-Pair Study

  As autonomous coding agents see rapid adoption, their evaluation has primarily focused on task completion rates holding the target codebase fixed. This leaves a critical question unanswered: does the structural and stylistic quality, or ``cleanliness'' of the underlying code affect an agent's abilit...

  📄 ResearchMay 19, 2026http://arxiv.org/abs/2605.20049v1
• OpenComputer: Verifiable Software Worlds for Computer-Use Agents

  We present OpenComputer, a verifier-grounded framework for constructing verifiable software worlds for computer-use agents. OpenComputer integrates four components: (1) app-specific state verifiers that expose structured inspection endpoints over real applications, (2) a self-evolving verification l...

  📄 ResearchMay 19, 2026http://arxiv.org/abs/2605.19769v1
• When to Answer and When to Defer: A Decision Framework for Reliable Code Predictions

  Code language models are increasingly adopted for both understanding and generative tasks. Despite their success, these models frequently produce overconfident incorrect predictions and underconfident correct predictions, undermining their reliability in deployment. Practical deployment demands thre...

  📄 ResearchMay 19, 2026http://arxiv.org/abs/2605.19369v1
• On-the-Fly Input Adaptation for Reliable Code Intelligence

  Code language models (CLMs) play a central role in software engineering across both generation and classification tasks. However, these models still exhibit notable mispredictions in real-world applications, even when trained on up-to-date data. Existing solutions address this by retraining the mode...

  📄 ResearchMay 19, 2026http://arxiv.org/abs/2605.19365v1
• MuMuTestUp: Mutation-based Multi-Agent Test Case Update

  Modern software systems evolve rapidly under CI/CD practices, where tests are critical for quality. However, substantial code changes often render existing test cases obsolete, causing pipeline disruptions, reduced productivity, and compromised quality. Recent automatic test update approaches levera...

  📄 ResearchMay 19, 2026http://arxiv.org/abs/2605.19265v1
• When Web Apps Heal Themselves: A MAPE-K Based Approach to Fault Tolerance and Adaptive Recovery

  Ensuring the reliability and resilience of modern web applications remains a critical challenge due to increasing system complexity and dynamic runtime environments. This study proposes a modular self-healing framework based on the monitor-analyze-plan-execute over a shared knowledge base (MAPE-K) m...

  📄 ResearchMay 19, 2026http://arxiv.org/abs/2605.19261v1
• Fast Multichannel NMF with Block-Diagonal Spatial Covariance Matrices for Efficient Blind Source Separation Using Distributed Microphone Arrays

  Distributed microphone arrays composed of multiple subarrays enable blind source separation over a wide spatial area. Directly applying fast multichannel nonnegative matrix factorization (FastMNMF) to all subarrays can exploit observations from all subarrays, but it requires repeated inversions of l...

  📄 ResearchMay 19, 2026http://arxiv.org/abs/2605.19388v1
• Divergence Meets Consensus: A Multi-Source Negative Sampling Framework for Sequential Recommendation

  Negative sampling is significant for training sequential recommendation models under implicit feedback. The predominant strategy, self-guided hard negative sampling, selects negatives based on the model's current state but suffers from three limitations: (1) the coupling between sampling and model u...

  📄 ResearchMay 19, 2026http://arxiv.org/abs/2605.19651v1
• Understanding Wacky Weights: A Dissection of SPLADE's Learned Term Importance

  Learned sparse retrieval models such as SPLADE combine the effectiveness of neural architectures with the efficiency of inverted indices. As these models assign weights to terms from a fixed vocabulary, interpretability is often touted as a major benefit of these models. However, the emergence of wa...

  📄 ResearchMay 19, 2026http://arxiv.org/abs/2605.19628v1
• The cost of efficiency in flexible neural representations

  Working memory depends on the flexible representation of stimulus information in neural activity, which changes dynamically depending on task. Stimulus transformations are thought to be efficient in use of neural resources and optimal for task performance. However, these transformations are often opaque, and efficiency may conflict with optimal performance. Here we show that in a working memory task requiring selective recall of one of two stimuli based on a context cue, the prefrontal cortex of two male monkeys prioritized efficiency by overwriting information within a shared neural subspace rather than maintaining distinct subspaces for each stimulus. In neural activity and recurrent neural networks such efficiency incurs a cost, in that efficient representations are more prone to errors. Conversely, stimulation of the cholinergic forebrain which improves behavior altered this default mechanism by encoding distinct contexts in higher dimensions. These findings demonstrate a fundament

  📄 ResearchMay 19, 2026https://www.biorxiv.org/content/10.64898/2026.05.18.722885v1?rss=1
• Developing a multi-modal neuroimaging-based BrainAge model across childhood

  BrainAge models hold promise as a clinical biomarker for developmental brain health, especially in childhood when there is the potential for early intervention. To distinguish between normative developmental variance and pathological divergence, BrainAge models should reflect the dynamic and diverse neurodevelopmental processes that occur in distinct developmental windows across childhood. We utilized multi-modal neuroimaging data from three pediatric cohorts covering ages 4 to 13 years (n = 1005, 2126 scans), split into Train and Test datasets. Twelve sex-stratified BrainAge models were built stratified by type and different combinations of neuroimaging features. Model types were 'Full-Span' models covering the full age range, and 'Phase-Specific' models split into early- and late-childhood. We first compared BrainAge estimates in the Test dataset amongst our candidate models, then benchmarked the best-performing model against published pre-trained models and DNA-based biological age

  📄 ResearchMay 19, 2026https://www.biorxiv.org/content/10.64898/2026.05.19.725847v1?rss=1
• AI interviewers can't connect with people the way human researchers can. They can produce only data, not meaning

  Anthropic, the company behind the generative AI tool Claude, claimed in March 2026 that it used an AI interviewer to conduct "the largest and most multilingual qualitative study" ever done. The AI tool collected responses from nearly 81,000 people about their visions for AI, spanning 70 languages and 159 countries. Anthropic contends that tools like this can enable researchers to conduct "rich, open-ended interviews at a very large scale."

  🌐 MovesMay 19, 2026https://techxplore.com/news/2026-05-ai-people-human.html
• AI can seem more human than real humans in a classic Turing test, study finds

  AI can seem more human than real humans in a classic Turing test, study finds EurekAlert!

  🌐 MovesMay 19, 2026https://www.eurekalert.org/news-releases/1128875
• Apple Taps Virtual Avatar Firm Animato's Expertise and Intellectual Property

  Apple has quietly agreed to hire employees and license intellectual property of Animato, a small California-based company that has developed software for creating virtual avatars used in video chats and tutoring, according to a European Commission filing spotted by MacRumors . The acquisition was filed under the EU's Digital Markets Act in January 2026, and appears to be what's known as a "structured acqui-hire." In other words, Apple is able to make employment offers to certain Animato employees and receive a non-exclusive license to the company's intellectual property, as well as acquire its patent applications. Apple Inc. ("Apple") will have the right to make employment offers to and hire certain employees of Animato, Inc. ("Animato"), receive a non-exclusive license to Animato's intellectual property rights, and acquire Animato's patent applications. Animato develops and distributes software that creates virtual avatars for video chats and tutoring. Animato was founded in October 2

  🌐 MovesMay 19, 2026https://www.macrumors.com/2026/05/19/apple-acquires-animato/
• Researchers improve AI’s ability to learn new tasks without sacrificing performance

  Researchers improve AI’s ability to learn new tasks without sacrificing performance EurekAlert!

  🌐 MovesMay 19, 2026https://www.eurekalert.org/news-releases/1128771
• Your favorite Google apps are getting a massive Gemini Live-like upgrade

  New conversational AI voice features are coming to Gmail, Keep, and Docs this summer to change how you work.

  🌐 MovesMay 19, 2026https://www.androidauthority.com/google-keep-docs-gmail-ai-voice-features-3668058/
• Apple just revealed an iOS 27 feature that hints at Siri’s new powers

  Today Apple announced its lineup of new accessibility features coming in iOS 27, iPadOS 27, macOS 27, and more, with an upgrade to Voice Control offering an exciting preview of agentic capabilities the new Siri will reportedly gain. more…

  🌐 MovesMay 19, 2026https://9to5mac.com/2026/05/19/apple-just-revealed-an-ios-27-feature-that-hints-at-siris-new-powers/
• Google is plugging the Play Store into Gemini for smarter app recommendations

  Forget searching the Play Store — just ask Gemini to find the best apps for your needs.

  🌐 MovesMay 19, 2026https://www.androidauthority.com/gemini-app-recommendations-3668243/
• GE Aerospace Just Did Something Amazing With AI

  GE Aerospace Just Did Something Amazing With AI Barron's

  🌐 MovesMay 19, 2026https://www.barrons.com/articles/ge-aerospace-stock-ai-engines-ff80963d?mod=RTA
• NewReputation's AI Sentiment Analysis Tool Reaches 2,500 Users as Businesses Demand Clearer Brand Intelligence

  NewReputation's AI Sentiment Analysis Tool Reaches 2,500 Users as Businesses Demand Clearer Brand Intelligence azcentral.com and The Arizona Republic

  🌐 MovesMay 19, 2026https://www.azcentral.com/press-release/story/71748/newreputations-ai-sentiment-analysis-tool-reaches-2500-users-as-businesses-demand-clearer-brand-intelligence/
• Trump shares AI-generated images of shackled alien and spaceships

  Trump shares AI-generated images of shackled alien and spaceships USA Today

  🌐 MovesMay 19, 2026https://www.usatoday.com/videos/news/2026/05/19/trump-shares-ai-generated-images-of-shackled-alien-and-spaceships/90156163007/
• Anthropic lets Glasswing partners publicly share Mythos flaws

  Anthropic lets Glasswing partners publicly share Mythos flaws IT Pro

  🌐 MovesMay 19, 2026https://www.itpro.com/technology/artificial-intelligence/anthropic-lets-glasswing-partners-publicly-share-mythos-flaws