PreprintNot peer reviewedArtificial IntelligenceResearchers report security flaws in world models used by AI agentsOriginal title: False Prophets: On the Security of World Models in Agentic SystemsA preprint finds text-based world models used by AI agents can be tricked into dangerous mispredictions up to 95% of the time.Erik Imgrund et al. · Added 4 Oct 2026
PreprintNot peer reviewedArtificial IntelligenceResearchers report encode-aware serving design boosts multimodal LLM throughputOriginal title: EAServe: Encode-Aware Disaggregated Serving for Multimodal Large Language ModelsA preprint proposes treating the Encode stage as the control point for serving multimodal LLMs, reporting large goodput gains over existing systems.Kunxiong Zhu et al. · Added 4 Oct 2026
Journal articleReview status unknownArtificial IntelligenceStudy tests ways to guide LLMs toward writing and fixing more secure codeOriginal title: Guiding AI to Fix Its Own Flaws: An Empirical Study on LLM-Driven Secure Code GenerationResearchers examine whether self-written vulnerability hints and detailed feedback help large language models avoid or repair insecure code.Hao Yan et al. · Added 4 Oct 2026
Journal articleReview status unknownQuantum ComputingResearchers report decoding gains for quantum codes using limited error-rate dataOriginal title: Enhancing Decoding Performance using Efficient Error LearningA study reports that feeding a decoder a small set of measured error rates sharply cuts logical error rates in concatenated quantum codes.Pavithran Iyer et al. · Added 4 Oct 2026 · Released Jul 2025
Journal article✓ Peer reviewedFrom Red Blue QuantumQuantum ComputingResearchers report faster protocol for preparing bosonic quantum error-correction statesOriginal title: Fast Bosonic Control via Multiphoton Qubit-Oscillator InteractionsA peer-reviewed study proposes multiphoton qubit-oscillator interactions that the authors say cut preparation times for bosonic codewords.Added 4 Oct 2026
Journal articleReview status unknownQuantum ComputingTheory study shows extra microwave tones can cut crosstalk in multiplexed qubit controlOriginal title: Active interference suppression in frequency-division-multiplexed quantum gates via off-resonant microwave tonesResearchers propose adding off-resonant microwave tones to suppress interference in frequency-multiplexed qubit control, reporting infidelity falling with more tones.Haruki Mitarai et al. · Added 4 Oct 2026 · Released Jun 2026
PreprintNot peer reviewedFrom GoogleArtificial IntelligenceSurvey maps how ‘agentic skills’ could make AI agents more reliable and secureOriginal title: A Systematic Survey of Agentic Skills: Architecture, Lifecycle, and SecurityA preprint surveys the emerging field of reusable 'agentic skills' for AI agents, covering design, memory, evaluation and security risks.Added 4 Oct 2026
Conference paperReview status unknownArtificial IntelligenceResearchers link knowledge graphs to LLM agents for automated hardware formal verificationOriginal title: Knowledge Graphs, the Missing Link in Agentic AI-based Formal VerificationA conference paper reports that a knowledge-graph-grounded multi-agent workflow improves LLM-generated formal assertions for hardware designs.Vaisakh Naduvodi Viswambharan et al. · Added 4 Oct 2026 · Released May 2026
PreprintNot peer reviewedArtificial IntelligenceA preprint describes ThinkingGuard, a guard model for detecting implicit multimodal safety risksOriginal title: ThinkingGuard: Decoding Implicit Hazards via Step-by-Step Risk Attribution in Multimodal Large Language ModelsA preprint presents a new dataset and training method that teach a guard model to reason about hidden safety risks across text and images.Ruochen Zhang et al. · Added 4 Oct 2026
PreprintNot peer reviewedArtificial IntelligenceA preprint reports a method to catch silent errors in LLM-generated optimisation codeOriginal title: ReLoop: Structured Modeling and Behavioral Verification for Reliable LLM-Based OptimizationResearchers describe ReLoop, a pipeline that combines structured prompting and solver-based checks to catch LLM optimisation code that runs fine but models the wrong problem.Junbo Jacob Lian et al. · Added 4 Oct 2026
PreprintNot peer reviewedArtificial IntelligenceSurvey maps how video generation models are post-trained to follow intent and stay coherentOriginal title: Video Generation Models: A Survey of Post-Training and AlignmentA preprint surveys methods for aligning pretrained video generation models with user intent, physics, and safety.Chaoyu Li et al. · Added 4 Oct 2026
Journal article✓ Peer reviewedFrom IBM QuantumQuantum ComputingResearchers trace quantum error-correction gate failures to measurement noise in superconducting chipOriginal title: Characterising the failure mechanisms of error-corrected quantum logic gatesA study on IBM's Marrakesh processor finds measurement noise is the main limit on fault-tolerant logic gate performance.Added 4 Oct 2026 · Released Apr 2025
Conference paperReview status unknownArtificial IntelligenceResearchers report LLMs often skip security protections in hardware code generationOriginal title: HardSecBench: Benchmarking the Security Awareness of LLMs for Hardware Code GenerationA new benchmark finds that LLMs frequently write functionally correct hardware code that still lacks important security protections.Qirui Chen et al. · Added 4 Oct 2026 · Released Jun 2026
Journal articleNot peer reviewedQuantum ComputingResearchers describe a noise-resilient quantum algorithm for computing system observablesOriginal title: Quantum Zeno Monte Carlo for computing observablesThe authors report a hybrid quantum-classical method that computes observables for gapped quantum systems with resistance to noise and Trotter errors.Mancheon Han et al. · Added 4 Oct 2026 · Released Jan 2025
PreprintNot peer reviewedQuantum ComputingA preprint extends quantum signal processing to non-commuting control for hybrid oscillator-qubit chipsOriginal title: Non-Abelian Quantum Signal Processing: A Composite Pulse for Fast Analytic Control of Hybrid Oscillator-Qubit ProcessorsA preprint introduces non-Abelian quantum signal processing, a single composite pulse said to speed up and unify control of oscillator-qubit quantum hardware.Shraddha Singh et al. · Added 4 Oct 2026
PreprintNot peer reviewedFrom Phasecraft and GoogleQuantum ComputingResearchers report digital quantum simulation of 2D Fermi-Hubbard model on 72 qubitsOriginal title: Programmable digital quantum simulation of 2D Fermi-Hubbard dynamics using 72 superconducting qubitsA preprint describes simulating 2D Fermi-Hubbard electron dynamics on a 72-qubit superconducting processor, benchmarked against classical methods.Added 28 Sep 2026
PreprintNot peer reviewedFrom IonQQuantum ComputingResearchers propose an ion-chain model and new error-correcting codes for trapped-ion qubitsOriginal title: Quantum error correction for long chains of trapped ionsA preprint models long trapped-ion chains and designs quantum LDPC codes that reportedly beat surface codes on qubit overhead.Added 28 Sep 2026 · Released Nov 2025
PreprintNot peer reviewedQuantum ComputingResearchers propose a multi-circuit approach to simulate quantum chemistry on near-term hardwareOriginal title: Nonorthogonal variational quantum simulation for quantum chemistryA preprint introduces NOVQS, combining several shallow quantum circuits to simulate chemical dynamics without deep circuits.Zongkang Zhang et al. · Added 28 Sep 2026
PreprintNot peer reviewedArtificial IntelligenceA preprint reports synthetic scientific coding problems that boost an LLM’s SciCode accuracyOriginal title: SciWalker: Synthesizing Scientific Coding Problems with Operator Graphs and Execution FeedbackResearchers describe SciWalker, a system that auto-generates scientific coding problems and reports large training gains on a 9B model.Chenxi Li et al. · Added 28 Sep 2026
PreprintNot peer reviewedArtificial IntelligenceA preprint reports a graph-based method for fairer step-level credit in agentic reinforcement learningOriginal title: Back to the Definition: Estimating Step-Level Advantages via Trajectory Graphs for Agentic Reinforcement LearningResearchers report a graph-based credit-assignment method, GRAFT, that improves multi-turn agentic RL over GRPO and similar baselines.Xincheng Yao et al. · Added 28 Sep 2026
