PreprintNot peer reviewedFrom HuaweiArtificial IntelligenceA preprint reports a skill-based approach to train long-horizon code agentsOriginal title: CodeSkill: Latent Skill Abstraction for Long-Horizon Code AgentsResearchers propose CodeSkill, a framework that abstracts code-agent trajectories into reusable skills to improve reinforcement learning efficiency.Added 30 Oct 2026
PreprintNot peer reviewedArtificial IntelligenceA preprint proposes requesting short LLM hints to cut costly inference while keeping accuracyOriginal title: Pay for Hints, Not Answers: LLM Shepherding for Cost-Efficient InferenceResearchers report that giving small models short prefixes from a large model, rather than full answers, cuts costs while preserving accuracy.Ziming Dong et al. · Added 30 Oct 2026
PreprintNot peer reviewedQuantum ComputingPreprint finds two uses cannot fix noisy qubit gates, but three canOriginal title: Distilling Qubit Unitary Operations: A No-Go Theorem and Minimal RealizationA preprint reports that purifying noisy single-qubit gates needs at least three uses of the channel, with two proven useless.Jiayi Zhao et al. · Added 30 Oct 2026
PreprintNot peer reviewedQuantum ComputingA preprint reports IQP circuits can solve the 2-Forrelation problemOriginal title: IQP circuits for 2-ForrelationA preprint shows commuting-gate IQP circuits can solve 2-Forrelation, answering an open question and giving a new oracle separation.Quentin Buzet et al. · Added 30 Oct 2026
PreprintNot peer reviewedArtificial IntelligencePreprint proposes closed-form hindsight credit assignment for long-horizon LLM agentsOriginal title: GraphHCA: Closed-Form Hindsight Credit Assignment for Long-Horizon LLM AgentsA preprint presents GraphHCA, a model-free method that derives step-level credit for LLM agents without an auxiliary hindsight model.Haodong Zhu et al. · Added 30 Oct 2026
PreprintNot peer reviewedFrom Kivira HealthArtificial IntelligencePreprint proposes K-Bench, a clinician-calibrated safety test for mental-health chatbotsOriginal title: K-Bench: a clinically calibrated benchmark for evaluating large language models in high-risk mental health conversationsA preprint describes K-Bench, a benchmark testing 125 AI model setups on simulated high-risk mental health conversations against clinician judgements.Added 30 Oct 2026
PreprintNot peer reviewedFrom Ant GroupArtificial IntelligencePreprint proposes relation tokens as building blocks for graph foundation modelsOriginal title: Relation-Aware Graph Foundation ModelA preprint introduces REEF, a graph foundation model that uses relation types rather than nodes or datasets as its basic unit for pre-training and transfer.Added 30 Oct 2026
PreprintNot peer reviewedQuantum ComputingA preprint reports quantum speedup for simulation-based decision optimisationOriginal title: Rate-Optimal Quantum Discrete Simulation OptimizationA preprint proposes QUEST, a quantum algorithm the authors say reaches optimal convergence for picking the best option under a fixed simulation budget.Mingjie Hu et al. · Added 30 Oct 2026
PreprintNot peer reviewedArtificial IntelligencePreprint proposes hybrid reward model that switches between fast and slow judgingOriginal title: Fast-Slow Thinking RM: Efficient Integration of Scalar and Generative Reward ModelsA preprint reports a reward model that mixes quick scalar scoring with chain-of-thought reasoning, cutting token use while keeping accuracy.Jiayun Wu et al. · Added 30 Oct 2026
PreprintNot peer reviewedFrom Pengxin Quantum TechnologyQuantum ComputingPreprint reports machine-checkable certificates for quantum code distancesOriginal title: Quantum code parameters, checkable by a certificate of provable sizeA preprint reports a Lean-verified certificate method that checks quantum error-correcting code distances instead of trusting solver outputs.Added 30 Oct 2026
PreprintNot peer reviewedArtificial IntelligencePreprint proposes letting reasoning models consult helper agents during trainingOriginal title: AIPO: Learning to Reason from Active InteractionA preprint reports a training method where language models query verification, knowledge and reasoning helpers mid-rollout to learn beyond their own exploration limits.Junnan Liu et al. · Added 30 Oct 2026
PreprintNot peer reviewedQuantum ComputingPreprint sets tight query bounds on faking quantum sampling scoresOriginal title: Tight Query Lower Bounds for Quantum Sampling, with an Application to Certified RandomnessA preprint proves tight limits on how many queries a device needs to beat the honest score in quantum sampling, with implications for certified randomness.Keshav Bhateja et al. · Added 30 Oct 2026
PreprintNot peer reviewedQuantum ComputingResearchers report first quantum-hardware calculation of scattering amplitudes via RESOsOriginal title: Scattering amplitudes from quantum hardware a la RESOsA preprint reports the first use of quantum hardware to compute scattering observables in a toy nuclear model using the RESOs method.Raul A Briceno et al. · Added 30 Oct 2026
PreprintNot peer reviewedArtificial IntelligenceStudy finds LLMs judge morality differently by language but reason similarly underneathOriginal title: One Model, Many Morals: Uncovering Cross-Linguistic Misalignments in Computational Moral ReasoningA preprint reports that language shifts LLMs' moral verdicts, yet their underlying reasoning stays broadly convergent across six languages.Sualeha Farid et al. · Added 30 Oct 2026
PreprintNot peer reviewedArtificial IntelligenceResearchers propose a reliability-engineering framework for autonomous and self-evolving AI systemsOriginal title: Reliability Engineering for AI Systems: Challenges, Methods, and DirectionsA preprint adapts classic reliability engineering—FMEA, monitoring, FRACAS—to assess AI agents and self-evolving systems beyond benchmark accuracy.Rong Pan et al. · Added 30 Oct 2026
PreprintNot peer reviewedArtificial IntelligenceResearchers build a taxonomy to profile how AI agents behave on everyday tasksOriginal title: AgentHabit: Characterizing Distinct Behaviors of Agents on Everyday TasksA preprint introduces HABIT and AgentHABIT, tools that profile 18 AI agents on 23 behavioural axes beyond task success.Woojung Song et al. · Added 30 Oct 2026
PreprintNot peer reviewedQuantum ComputingA preprint reports a faster, QFT-free quantum algorithm for symmetric-group charactersOriginal title: An efficient Hamiltonian-based quantum algorithm for characters of the symmetric groupResearchers describe a Hamiltonian-based method to prepare symmetric-group character states using fewer gates than prior quantum Fourier transform approaches.Dikshant Rathore et al. · Added 30 Oct 2026
PreprintNot peer reviewedQuantum ComputingPreprint studies how encoding and node choices affect distributed quantum error ratesOriginal title: Encoding and Node Choices in Transversal Fault-Tolerant Distributed Quantum Computations: An Initial StudyA preprint examines how choosing different Bivariate-Bicycle code encodings and node setups affects error rates in distributed quantum computing.Seng W. Loke · Added 30 Oct 2026
PreprintNot peer reviewedFrom Adobe ResearchArtificial IntelligencePreprint proposes splitting long-context reasoning across worker and driver LLMsOriginal title: DISCO: Distributed Long Context Scaling with Grounding-Reasoning DisaggregationA preprint reports that disaggregating grounding from reasoning across distributed LLMs curbs long-context accuracy collapse.Added 30 Oct 2026
PreprintNot peer reviewedQuantum ComputingResearchers report streaming method for partial-transpose moments using fixed quantum memoryOriginal title: Streaming the partial-transpose moment hierarchy with order-independent quantum memoryA preprint describes a streaming protocol that estimates entanglement-revealing moments without needing more quantum memory as moment order grows.Junxiang Huang et al. · Added 30 Oct 2026
