PreprintNot peer reviewedArtificial IntelligenceResearchers report LLM-based red teaming framework severely degrades DRL cyber defendersOriginal title: Trident : How to Break Deep Reinforcement Learning Cyber Defenses (Agentic)A preprint introduces Trident, an LLM agent trained via reinforcement learning that the authors report sharply weakens autonomous cyber defenders.Ryozo Masukawa et al. · Added 28 Sep 2026
PreprintNot peer reviewedArtificial IntelligenceA preprint introduces Benchmark Radar, a searchable database of AI evaluation benchmarksOriginal title: Benchmark Radar: A Living Database and Search Engine for AI Benchmarks and EvaluationThe authors describe a living catalog and search tool for finding AI benchmarks, their datasets, code and reported scores.Koutian Wu et al. · Added 28 Sep 2026
PreprintNot peer reviewedArtificial IntelligenceResearchers report a calibrated-answer model detects many AI alignment failures without fine-tuningOriginal title: Just Ask Jev: Reinforcement Learning for Calibrated Decisions as a Zero-Shot Detector of AI Alignment FailuresA preprint finds that a single generic question to the Jev model ranks most alignment failures well, at much lower cost than judge models.Ruoqi Guo et al. · Added 28 Sep 2026
Preprint✓ Peer reviewedFrom AmazonQuantum ComputingResearchers report neutral-atom platform combining fault-tolerant quantum computing elementsOriginal title: Architectural mechanisms of a universal fault-tolerant quantum computerA preprint reports experiments on a 448-atom neutral-atom system demonstrating key fault-tolerant quantum computing architecture elements together.Added 28 Sep 2026 · Released Jun 2025
Journal article✓ Peer reviewedQuantum ComputingResearchers report constant-depth non-Clifford gates in 2D using non-Abelian surface codesOriginal title: Constant-Depth Clifford-Hierarchy Gates via Non-Abelian Surface CodesA study describes constant-depth logical phase gates at arbitrary Clifford-hierarchy levels using 2D non-Abelian surface codes.Alison Warman et al. · Added 28 Sep 2026
Journal articleReview status unknownQuantum ComputingResearchers report crystalline oxide-nitride stack could cut dielectric loss in qubit circuitsOriginal title: Oxide-Nitride Heteroepitaxy for Low-Loss Dielectrics in Superconducting Quantum CircuitsA journal study reports a crystalline TiN/aluminium oxide/TiN trilayer with very low measured microwave dielectric loss.David A. Garcia-Wetten et al. · Added 28 Sep 2026
Conference paperReview status unknownArtificial IntelligenceResearchers report robot backdoors triggered by the robot’s own actionsOriginal title: Silent Sabotage: Internal State Triggered Backdoor Attacks on LLM-Powered Robotic SystemsResearchers demonstrate a stealthy backdoor in LLM-controlled robots that activates only after a rare sequence of the robot's own prior actions.Doniyorkhon Obidov et al. · Added 28 Sep 2026
PreprintNot peer reviewedArtificial IntelligenceA preprint reports a scanner that spots poisoned code-generation models with 97%+ accuracyOriginal title: Detecting Data Poisoning in Code Generation LLMs via Black-Box, Vulnerability-Oriented ScanningResearchers describe CodeScan, a black-box method to detect poisoned or backdoored code-generation models by scanning for known vulnerability patterns.Shenao Yan et al. · Added 28 Sep 2026
Journal articleReview status unknownQuantum ComputingHow laser phase noise limits a key trapped-ion entangling gateOriginal title: Influence of fast and slow laser phase noise on the fidelity of the Mølmer-Sørensen trapped-ion gateA Quantum Reports study analyses how fast and slow laser phase noise affects the fidelity of the Mølmer–Sørensen trapped-ion gate.Nikita Semenin et al. · Added 27 Sep 2026
Conference paperReview status unknownQuantum ComputingQBugLM benchmarks how well LLMs debug quantum programsOriginal title: QBugLM: An Agentic Benchmarking Framework for LLM-based Quantum Software DebuggingAn IEEE quantum software conference paper introduces QBugLM, a multi-agent framework that tests how well two LLMs detect and repair bugs in quantum programs.An B. B. Pham et al. · Added 27 Sep 2026 · Released Jun 2026
Journal article✓ Peer reviewedArtificial IntelligenceDynamic defence uses a model’s own layers to resist LLM jailbreaksOriginal title: Dynamic Deep Prompt Optimization for Defending Against Jailbreak Attacks on LLMsAn AAAI conference paper introduces a method that generates defensive embeddings from a model's own layers to resist jailbreak attacks.Doniyorkhon Obidov et al. · Added 27 Sep 2026 · Released Mar 2026
