PreprintNot peer reviewedFrom QuEra ComputingQuantum ComputingResearchers propose multi-agent LLM system for quantum circuit compilationOriginal title: Qubrio: High-Performance Quantum Compilation via Multi-Agent LLM CollaborationA preprint describes Qubrio, a multi-agent LLM framework that compiles quantum circuits for neutral-atom hardware, reporting gains over a prior heuristic compiler.Added 8 Nov 2026
Journal articleReview status unknownArtificial IntelligenceMapping study finds LLM-driven game NPCs lack shared benchmarks and safety checksOriginal title: LLM-based NPCs in Video Games: A Systematic Mapping StudyA systematic review of 42 papers finds LLM-based NPCs vary widely in design, with memory, safety and reproducibility gaps.Dilan Mian et al. · Added 8 Nov 2026 · Released Jan 2026
PreprintNot peer reviewedArtificial IntelligenceResearchers report a jailbreak that abuses function-calling workflows in LLMsOriginal title: Beyond the Prompt: Jailbreaking Function-Calling LLMs via Simulated Moderation TracesA preprint describes SMT, an attack that fakes moderation feedback inside tool-calling sessions to push LLMs toward harmful outputs.Junlong Liu et al. · Added 8 Nov 2026
Journal articleReview status unknownQuantum ComputingResearchers report fast, high-fidelity microwave qubit gate using Autler-Townes effectOriginal title: Autler-townes energy-level engineering for high-quality all-microwave qubit gateA study reports a 97 ns all-microwave CZ gate reaching 99.40(9)% fidelity by engineering qubit energy levels.Wan-Peng Gao et al. · Added 8 Nov 2026
PreprintNot peer reviewedFrom HuaweiArtificial IntelligenceResearchers report a KV cache offloading design for faster long-context LLM servingOriginal title: FlashOffloading: Low-Latency KV Cache Offloading for Long-Context LLM ServingA preprint describes FlashOffloading, which moves KV cache data to host DRAM to raise throughput for long-context LLM inference.Added 8 Nov 2026
PreprintNot peer reviewedFrom Peeramid LabsArtificial IntelligencePreprint proposes consensus method for combining separate LLMs without a central aggregatorOriginal title: Mixture-of-Models: Distributed Inference over Heterogeneous LLMs as Model-Level Mixture-of-ExpertsA preprint describes a protocol letting independently trained language models reach consensus through peer voting rather than a central aggregator model.Added 8 Nov 2026
Journal articleReview status unknownQuantum ComputingResearchers report bit-flip noise hits QAOA harder than phase-flip noiseOriginal title: Asymmetric quantum error correction efficiently tackles application-specific noise effectsA study of a small flight-gate scheduling problem finds bit-flip errors degrade QAOA results more than phase-flip errors, suggesting tailored error correction.Abhishek Yadav et al. · Added 8 Nov 2026
PreprintNot peer reviewedArtificial IntelligenceNew evaluation framework finds LLM compression hurts abilities unevenlyOriginal title: ACE-Compression: An Ability-Centric Evaluation of Compressed Large Language ModelsA preprint introduces an ability-focused test suite showing that compressing LLMs can quietly erode specific skills even when overall scores look fine.Jiahui Ning et al. · Added 8 Nov 2026
PreprintNot peer reviewedArtificial IntelligenceA preprint reports an adaptive token-budget scheduler to cut LLM serving latencyOriginal title: P-PAS: Prefill-Pressure Adaptive Scheduling for Long-Context LLM ServingResearchers propose P-PAS, a vLLM scheduling policy that adapts token budgets to prefill pressure, reportedly lowering latency for long-context LLM serving.Timo Sämann · Added 8 Nov 2026
PreprintNot peer reviewedArtificial IntelligenceResearchers locate ‘value heads’ in LLMs to steer alignment without retrainingOriginal title: Towards Multi-Value Alignment via Value Localization in LLMsA preprint reports that specific attention heads in LLMs encode distinct human values, enabling inference-time control without fine-tuning.Xueqi Ma et al. · Added 8 Nov 2026
PreprintNot peer reviewedFrom MicrosoftArtificial IntelligenceA preprint reports a benchmark exposing weak privacy-utility trade-offs in DP text generationOriginal title: SynBench: A Benchmark for Differentially Private Text GenerationA preprint introduces SynBench, finding current differentially private text generators struggle with domain data and still leak membership signals.Added 8 Nov 2026
Journal articleReview status unknownQuantum ComputingResearchers propose entanglement purification using travelling qubits instead of stored pairsOriginal title: Carrier-Assisted Entanglement PurificationA study outlines a purification protocol that swaps bulky quantum memory demands for single qubits sent between parties.Jaemin Kim et al. · Added 8 Nov 2026 · Released Jan 2026
PreprintNot peer reviewedFrom Ant GroupArtificial IntelligenceA preprint reports a tunable safety dial for LLMs via expert upcyclingOriginal title: UpSafe$^\circ$C: Upcycling for Controllable Safety in Large Language ModelsResearchers report converting safety-critical layers into a mixture-of-experts structure with a tunable safety knob, improving safety while keeping general task performance.Added 8 Nov 2026
Journal article✓ Peer reviewedFrom PsiQuantumQuantum ComputingExact maths links toric code error rates to the solvable 2D Ising modelOriginal title: Ising on the donut: Regimes of topological quantum error correction from statistical mechanicsThe study derives closed-form error-rate formulas for a post-selected toric code by mapping it exactly to the 2D Ising model.Added 7 Nov 2026
PreprintNot peer reviewedFrom ToshibaArtificial IntelligenceResearchers report LLMs spot unsafe actions but struggle to plan safely over timeOriginal title: CAPSafe: A Benchmark for Contextual Action and Plan Safety Reasoning in Embodied AgentsA preprint benchmark finds language-model agents are good at flagging unsafe actions but much weaker at generating safe long multi-step plans.Added 7 Nov 2026
Journal article✓ Peer reviewedFrom IBMQuantum ComputingEntanglement can boost sensing of correlated dephasing noise, study findsOriginal title: Exponential entanglement advantage in sensing correlated noisePhysicists report that entangled sensors can gain an exponential edge when measuring correlated noise fluctuations, unlike with uncorrelated noise.Added 7 Nov 2026
PreprintNot peer reviewedFrom Alibaba (DAMO Academy)Artificial IntelligenceResearchers report multimodal AI models hallucinate far more under adversarial fuzz testingOriginal title: Unified Hallucination Fuzzing for Multimodal Large Language ModelsA preprint introduces a fuzzing framework showing that leading multimodal AI models hallucinate much more once inputs are adversarially mutated.Added 7 Nov 2026
Journal article✓ Peer reviewedQuantum ComputingScheduling trick cuts GPU communication overhead in quantum circuit simulationOriginal title: Lazy Qubit Reordering for Accelerating Parallel State-Vector-based Quantum Circuit SimulationResearchers report scheduling methods that delay qubit reordering to speed up multi-GPU quantum circuit simulation.Yusuke Teranishi et al. · Added 7 Nov 2026 · Released Oct 2024
PreprintNot peer reviewedFrom PocketFMArtificial IntelligencePreprint compares 10 prompting styles for moral reasoning and safety across four LLMsOriginal title: ProMoral-Bench: Evaluating Prompting Strategies for Moral Reasoning and Safety in LLMsA preprint reports that compact, example-based prompts often beat elaborate multi-stage scaffolds on moral judgment and safety trade-offs in large language models.Added 7 Nov 2026
Conference paperReview status unknownFrom AccentureArtificial IntelligenceResearchers unify tools for scaling LLM reasoning compute at test timeOriginal title: ThinkBooster: A Unified Framework for Seamless Test-Time Scaling of LLM ReasoningA conference paper introduces ThinkBooster, a toolkit and benchmark for comparing test-time reasoning strategies on cost and accuracy.Added 7 Nov 2026 · Released Jan 2026
