PreprintNot peer reviewedArtificial IntelligencePreprint proposes unified reward model to train memory agents jointly, not in isolationOriginal title: All-in-One Memory: Process-Rewarded Reinforcement Learning for Memory AgentsA preprint presents AiO-Mem, which trains retrieval and memory writing together using one shared reward signal.Bingbing Wang et al. · Added 3 Nov 2026
PreprintNot peer reviewedQuantum ComputingA preprint reports a decoder that splits qubit readout errors into distinct channelsOriginal title: Syndrome-Resolved Decoding of Qubit Readout ErrorsResearchers propose RED, a method that decodes repeated binary qubit readouts to separate assignment, bit-flip and leakage errors.Han Zheng et al. · Added 3 Nov 2026
PreprintNot peer reviewedFrom Multiverse ComputingArtificial IntelligenceResearchers report fixes for slow remote KV caching in long-context LLM servingOriginal title: When the KV Cache Is Slower Than the GPU: Scaling Remote KV Tiers for Context-Parallel PrefillA preprint explains why a shared KV cache tier can be slower than recomputation, and reports fixes that cut tail latency sharply.Added 3 Nov 2026
PreprintNot peer reviewedFrom QMillQuantum ComputingPreprint examines how quantum circuit results diverge across cloud providersOriginal title: Realization Divergence in Multi-Provider Quantum Computing: A Pre-Registered Study of What Survives MeasurementA preprint reports that qubit placement, not circuit size, best explains differing compiled-circuit overheads across quantum hardware providers.Added 3 Nov 2026
PreprintNot peer reviewedArtificial IntelligenceResearchers report multi-model system beats single-LLM pipelines for code generationOriginal title: Multi-LLM Orchestration for High-Quality Code Generation: Exploiting Complementary Model StrengthsA preprint describes PerfOrch, which assigns different LLMs to generate, debug and refine code, reporting higher accuracy and faster programs than single-model approaches.Huashan Chen et al. · Added 3 Nov 2026
PreprintNot peer reviewedFrom IBMArtificial IntelligenceA preprint reports a KV-cache eviction method with speed and accuracy gainsOriginal title: DropKV: Decoupling Residual-Output Perturbation for Near-Optimal KV-Cache EvictionA preprint describes DropKV, a per-token KV-cache eviction scheme that the authors say gives near-optimal accuracy with faster inference.Added 3 Nov 2026
PreprintNot peer reviewedQuantum ComputingResearchers report sparse generators cut gate counts in quantum imaginary-time evolutionOriginal title: Sparse-QITE: Discovering Compact Generators for Quantum Imaginary-Time Evolution via Regularization MethodsA preprint introduces Sparse-QITE, which uses regularisation to shrink circuit size for quantum ground-state preparation while keeping accuracy.Rafael Gómez-Lurbe et al. · Added 3 Nov 2026
PreprintNot peer reviewedFrom Prentis AIArtificial IntelligenceResearchers report a new GUI grounding dataset and training method for screen-interaction modelsOriginal title: GroundGUI: GUI Grounding by High-Quality Data and Distillation-to-Reinforcement LearningA preprint introduces a large GUI grounding dataset and a two-stage training method, reporting strong results for an 8-billion-parameter model.Added 3 Nov 2026
PreprintNot peer reviewedFrom TencentArtificial IntelligenceResearchers report video AI models often trust misleading on-screen captions over the footageOriginal title: VisualTrust: Video Reasoning under On-Screen Claim FramingA preprint finds video language models often accept a false on-screen claim over visual evidence, and proposes an agent that largely restores accuracy.Added 3 Nov 2026
PreprintNot peer reviewedArtificial IntelligenceSurvey maps how LLM agent actions can be traced and audited for trustOriginal title: From Agent Traces to Trust: A Survey of Evidence Tracing and Execution Provenance in LLM AgentsA preprint surveys methods for tracing evidence and execution steps in LLM agents, finding major gaps in current benchmarks.Yiqi Wang et al. · Added 3 Nov 2026
PreprintNot peer reviewedQuantum ComputingPreprint argues quantum computers still face signal-to-noise limits despite avoiding sign problemsOriginal title: Signal-to-noise problems in fault-tolerant quantum computationA preprint contends that fault-tolerant quantum computers avoid the classical sign problem but still suffer exponentially growing sampling noise.Hyunwoo Oh · Added 3 Nov 2026
PreprintNot peer reviewedFrom Beijing Yuanjie Exploration Quantum TechnologyQuantum ComputingResearchers report framework linking algorithm design to surface-code hardware layoutOriginal title: Low-cost algorithm-to-execution framework for surface-code quantum computingA preprint describes a framework that tailors surface-code quantum layouts to specific algorithms, reporting large cuts in modelled resource costs.Added 3 Nov 2026
PreprintNot peer reviewedFrom Valeo.aiArtificial IntelligenceResearchers report self-supervised tasks sharpen MLLM visual groundingOriginal title: V-GIFT: Boosting Visual Instruction Tuning with Self-Supervised GuidanceA preprint reports that mixing a small share of self-supervised visual tasks into instruction tuning improves vision-centric performance in multimodal language models.Added 3 Nov 2026
PreprintNot peer reviewedQuantum ComputingPreprint links exact Floquet recurrences to number theory and quantum ‘magic’Original title: Cyclotomic Structure and Exact Recurrences in Floquet Many-Body Quantum DynamicsA preprint reports an arithmetic test for when periodically driven quantum systems return to their starting state exactly.Amit Anand et al. · Added 3 Nov 2026
PreprintNot peer reviewedFrom SAPArtificial IntelligenceA preprint reports TabFORGE, a foundation model for generating synthetic tabular dataOriginal title: TabFORGE: A Tabular Foundation Model for Generative ModellingThe authors report that a new pretrained generator for tabular data better preserves feature dependencies than prior foundation models and dataset-specific baselines.Added 3 Nov 2026
PreprintNot peer reviewedArtificial IntelligencePreprint proposes method to infer an LLM’s pretraining data mix from its output textOriginal title: LLMSurgeon: Diagnosing Data Mixture of Large Language ModelsA preprint describes LLMSurgeon, which estimates a language model's pretraining domain mixture using only generated text.Yaxin Luo et al. · Added 3 Nov 2026
PreprintNot peer reviewedQuantum ComputingPreprint reports local error correction extends time-crystal memory on quantum chipOriginal title: Local error correction prolongs time-crystalline memoryA preprint reports that stochastic bit-flip correction roughly doubled how long a superconducting processor sustained a time-crystal-like response.Benedikt Fauseweh · Added 3 Nov 2026
PreprintNot peer reviewedFrom EvenUpArtificial IntelligenceA preprint reports an agent that lets small models handle long document QAOriginal title: DocPilot: Interactive Agent Orchestration and Training for Long Visual Document UnderstandingThe authors describe DocPilot, a trainable document agent that pairs adaptive evidence-seeking with curriculum training to help compact models rival larger VLMs.Added 3 Nov 2026
PreprintNot peer reviewedQuantum ComputingPreprint maps which quantum states can directly power magic gate teleportationOriginal title: Magic Gate Teleportation: Structure, Useful Resource States, and Simpler FeedforwardA preprint analyses which non-stabiliser quantum states can directly implement non-Clifford gates via teleportation, and when feedforward can be simplified.Yunzhe Zheng et al. · Added 3 Nov 2026
PreprintNot peer reviewedQuantum ComputingPreprint explores how detecting qubit loss could sharpen quantum sensing limitsOriginal title: Optimal quantum metrology protocols with erasure qubitsA preprint analyses how detectable erasure noise reshapes precision limits and optimal strategies for single-qubit quantum sensing.Michal Arieli et al. · Added 3 Nov 2026
