PreprintNot peer reviewedFrom MetaArtificial IntelligenceResearchers report LLM agents designing new neural network architectures autonomouslyOriginal title: Agentic Discovery of Neural Architectures: AIRA-Compose and AIRA-DesignA preprint describes LLM agents that design and test new foundation-model architectures, some beating human baselines.Added 23 Oct 2026
PreprintNot peer reviewedQuantum ComputingPreprint proposes hierarchical processor to cut quantum error-correction overheadOriginal title: Hierarchical Quantum Logical Processor with Amortized Long-Range ConnectivityA preprint describes a layered quantum code architecture that authors say needs far fewer qubits and faster error-correction cycles.Zi-Han Chen et al. · Added 23 Oct 2026
PreprintNot peer reviewedArtificial IntelligenceStudy audits privacy risks introduced by LLM-enhanced graph neural networksOriginal title: Auditing Privacy Risks in LLM-Enhanced Graph Neural NetworksA preprint reports that enriching GNN node features with LLM-generated semantics raises exposure to link, label and membership inference attacks.Longzhu He et al. · Added 23 Oct 2026
PreprintNot peer reviewedArtificial IntelligenceA preprint finds LLM vulnerability-patching benchmarks easily inflated by evaluation designOriginal title: On the Reliability of LLM-Based Vulnerability Patching BenchmarksA preprint reports that small changes to how patching benchmarks are run can sharply shift headline pass rates without improving real fix quality.Dang K Le et al. · Added 23 Oct 2026
PreprintNot peer reviewedFrom Zurich InstrumentsQuantum ComputingResearchers report spiking neural networks for real-time qubit readout on FPGAsOriginal title: Spiking neural networks for streaming qubit readoutA preprint reports spiking neural networks that classify superconducting qubit states as data arrives, nearly matching full-trace networks with FPGA-ready speed.Added 23 Oct 2026
PreprintNot peer reviewedArtificial IntelligenceMulti-agent framework with rubric RL reports strong gains on end-to-end GPU code generationOriginal title: StitchCUDA: An Automated Multi-Agents End-to-End GPU Programing Framework with Rubric-based Agentic Reinforcement LearningA preprint describes StitchCUDA, a three-agent GPU programming system trained with rubric-based reinforcement learning to improve end-to-end code generation.Shiyang Li et al. · Added 23 Oct 2026
PreprintNot peer reviewedFrom NEC Labs AmericaArtificial IntelligenceA preprint reports per-query multi-agent system design beats fixed workflowsOriginal title: OOPMAS: Object-Oriented Multi-Agent Systems for Query-Level Workflow GenerationA preprint describes OOPMAS, which builds a custom agent team and workflow for each query rather than reusing one fixed design.Added 23 Oct 2026
PreprintNot peer reviewedArtificial IntelligencePreprint proposes DynaCore, a reshaped chip design for faster LLM servingOriginal title: A Shape-Adaptive Architecture with Disaggregated Quantization for Efficient LLM ServingA preprint describes a chip architecture that adapts to both the prefill and decoding phases of LLM inference to cut serving delays.Cong Guo et al. · Added 23 Oct 2026
PreprintNot peer reviewedArtificial IntelligenceResearchers report security risks hidden in efficiency-focused speculative decoding for LLMsOriginal title: Secure Speculative Decoding for Large Language ModelsA preprint finds that faster, lossy speculative decoding methods sharply raise jailbreak and prompt-injection risks while barely affecting utility scores.Yichi Zhang et al. · Added 23 Oct 2026
PreprintNot peer reviewedArtificial IntelligenceSurvey maps mismatches between RAG attacks and defencesOriginal title: A Survey of Secure Retrieval-Augmented GenerationA preprint survey of 135 studies finds RAG security attacks and defences are unevenly matched across targets, stages and signals.Yuming Xu et al. · Added 23 Oct 2026
PreprintNot peer reviewedFrom IBM ResearchQuantum ComputingPreprint explores quantum speedups beyond worst-case inputsOriginal title: Quantum Query Complexity Beyond the Worst CaseA preprint applies smoothed analysis to quantum query complexity, reporting large speedups on perturbed string problems.Added 23 Oct 2026
PreprintNot peer reviewedArtificial IntelligenceStudy maps how language models recover after acting on false premisesOriginal title: PHRBench: A Behavioral Evaluation of Post-Hallucination Reasoning in LLMsA preprint introduces PHRBench, finding that models rarely correct hallucinated premises, but recovery can be predicted beforehand.Linghao Meng et al. · Added 23 Oct 2026
PreprintNot peer reviewedFrom Pathfinder Applied ResearchArtificial IntelligenceResearchers propose topology-based signals to detect and steer ill-posed LLM promptsOriginal title: TIPS: Topological Ill-Posedness Probing and Steering in Large Language ModelsA preprint reports that shape-based features of internal model states can flag ambiguous questions and guide LLMs to clarify or abstain.Added 23 Oct 2026
PreprintNot peer reviewedArtificial IntelligencePreprint proposes skill lifecycle so LLM agent skill libraries don’t go stale during RLOriginal title: SkillForge: Co-Evolving Skills and Agents via Dynamic Skill LifecyclesA preprint describes SkillForge, which retires and mutates outdated agent skills during reinforcement learning rather than letting libraries grow unchecked.Yuyao Ge et al. · Added 23 Oct 2026
PreprintNot peer reviewedFrom XiaohongshuArtificial IntelligenceResearchers propose graph-based credit scoring to fix step selection in LLM agent distillationOriginal title: GraphOPD: Graph-Augmented On-Policy Distillation for LLM AgentsA preprint reports that routing teacher guidance to steps with high structural impact, not just high disagreement, improves agent training on several benchmarks.Added 23 Oct 2026
PreprintNot peer reviewedQuantum ComputingPreprint reports modular neural decoder portable across quantum hardware and logic typesOriginal title: Modular Neural Decoder for Surface Code Memory and Logic on Superconducting ProcessorsA preprint describes a compact, reusable neural decoder that beats standard matching methods across memory, stability and lattice-surgery experiments on real quantum hardware.Moritz Lange et al. · Added 23 Oct 2026
PreprintNot peer reviewedArtificial IntelligenceResearchers report decoding method cuts LLM hallucinations without retrainingOriginal title: APCD: Adaptive Path-Contrastive Decoding for Reliable Large Language Model GenerationA preprint describes a multi-path decoding technique that the authors say improves factual accuracy across several language models.Tianyu Zheng et al. · Added 23 Oct 2026
PreprintNot peer reviewedQuantum ComputingPreprint proposes correlation-based shortcuts for learning large quantum systemsOriginal title: A Few Constrain Many: Correlation-Enhanced Learning of Many-Body Quantum SystemsA preprint reports that correlations between quantum observables can cut the measurements needed to estimate entanglement and magic in 100-qubit systems.Matteo Tedde et al. · Added 23 Oct 2026
PreprintNot peer reviewedQuantum ComputingPreprint proposes systematic search framework for single-ancilla fault-tolerant error correctionOriginal title: Bare-ancilla fault-tolerant syndrome extraction: General extensions of distance-three codes and structural criteria for graph codesA preprint describes a general method for finding bare-ancilla fault-tolerant codes and reports extensions that enlarge valid code sets while keeping distance fixed.Harsh Gupta et al. · Added 23 Oct 2026
PreprintNot peer reviewedQuantum ComputingResearchers propose letting shuttled spin qubits leapfrog over occupied dots in siliconOriginal title: Spin Qubit Leapfrogging: Dynamics of shuttling electrons on top of anotherA preprint models a way for a mobile spin qubit to pass through an occupied quantum dot, exploiting low valley splitting to perform a two-qubit gate.Nicklas Meineke et al. · Added 23 Oct 2026
