PreprintNot peer reviewedArtificial IntelligencePreprint proposes lightweight controllers to cut multi-agent LLM coordination costsOriginal title: Token-Efficient Multi-Agent Collaboration via System One-Guided Computational Division of LaborA preprint reports that routing coordination decisions to small models instead of large LLMs cuts token use and latency while keeping accuracy high.Zihan Zhou et al. · Added 24 Oct 2026
PreprintNot peer reviewedQuantum ComputingPreprint proposes hardware-aware aggregation for quantum federated learning on noisy devicesOriginal title: Q-RAIL: A Reliability-Aware Framework for Quantum Federated Learning on Heterogeneous Noisy HardwareA preprint reports that weighting client updates by backend noise and circuit statistics improves quantum federated learning accuracy on simulated heterogeneous hardware.Walid El Maouaki et al. · Added 24 Oct 2026
PreprintNot peer reviewedArtificial IntelligenceResearchers link LLMs’ behaviour in cooperation games to multi-agent science task performanceOriginal title: Cooperative Profiles Predict Multi-Agent LLM Team Performance in AI for Science WorkflowsA preprint reports that how LLMs behave in behavioural economics games predicts their performance as AI-for-Science collaborators.Shivani Kumar et al. · Added 24 Oct 2026
PreprintNot peer reviewedQuantum ComputingA preprint reports an HDL-built Falcon accelerator fitting on one FPGAOriginal title: Peregrino: A Full-Hardware Accelerator for the Complete Falcon Post-Quantum Digital Signature Scheme on Resource-Constrained Edge DevicesResearchers describe Peregrino, a hand-written hardware accelerator for the full Falcon post-quantum signature scheme on a single FPGA.Antonio Carreño et al. · Added 24 Oct 2026
PreprintNot peer reviewedFrom NVIDIAArtificial IntelligenceA preprint reports frozen medical AI models can improve via external expertise, not retrainingOriginal title: Frozen Models, Evolving Expertise: Model-Agnostic Learning from Deployment Experience for Multimodal Medical AIResearchers report a framework letting frozen language and vision-language models improve in medicine by storing skills, facts and images rather than retraining.Added 24 Oct 2026
PreprintNot peer reviewedQuantum ComputingPreprint reports a coherent atom-molecule quantum interface using tweezer-trapped particlesOriginal title: A coherent quantum interface between a neutral atom and a polar moleculeResearchers report linking a single trapped atom and molecule for quantum readout, spin exchange and entanglement.Daniel K. Ruttley et al. · Added 24 Oct 2026
PreprintNot peer reviewedArtificial IntelligenceA preprint reports multi-agent framework with causal graph boosts vulnerability detection accuracyOriginal title: CLEAR: Causal Context-Based Agentic Reasoning for Vulnerability DetectionResearchers propose CLEAR, a multi-agent system using a causal knowledge graph to better distinguish vulnerable from benign code.Sungju Yun et al. · Added 24 Oct 2026
PreprintNot peer reviewedQuantum ComputingPreprint reports ASIC design makes Mirath signatures faster and smaller than SLH-DSAOriginal title: Efficient TCitH-Based Alternatives to SLH-DSA: Cross-Layer ASIC Design of MirathA preprint describes the first ASIC build of the Mirath post-quantum signature scheme, reporting large speed and area gains over SLH-DSA.Hiandra Tomasi et al. · Added 24 Oct 2026
PreprintNot peer reviewedArtificial IntelligenceResearchers show open-weight LLM safeguards can be jailbroken without fine-tuningOriginal title: Open-Weight LLM Fine-Tuning Defenses are Susceptible to Simple AttacksA preprint finds that simple, no-training attacks bypass fine-tuning defenses meant to stop misuse of open-weight language models.Kevin Kuo et al. · Added 24 Oct 2026
PreprintNot peer reviewedQuantum ComputingPreprint proposes quantum algorithm for nonlinear PDEs using homotopy analysisOriginal title: Quantum Homotopy Algorithm for Solving Nonlinear PDEs and Flow ProblemsResearchers outline a hybrid quantum method for solving nonlinear flow equations and test it with classical simulations of the homotopy approximation.Sachin S. Bharadwaj et al. · Added 24 Oct 2026
PreprintNot peer reviewedFrom logsight.aiArtificial IntelligenceResearchers report dual-AI framework for robot control via natural languageOriginal title: Adaptive Code Generation for Controlling RobotsA preprint describes an LLM-and-VLM architecture letting robots turn open-ended language goals into verified, adaptable code.Added 24 Oct 2026
PreprintNot peer reviewedQuantum ComputingA preprint proposes an algorithm for allocating scarce quantum-safe links across networksOriginal title: WLPA: A Network Management Framework for Allocating Scarce Quantum-Safe Link Postures under Weakest-Link ExposureA preprint describes WLPA, a framework that allocates limited quantum-safe link upgrades by protecting a job's weakest link rather than ranking links individually.Bhanwar Gupta et al. · Added 24 Oct 2026
PreprintNot peer reviewedFrom Hewlett Packard EnterpriseArtificial IntelligencePreprint proposes probing LLM internals, not just benchmark scores, to spot hidden flawsOriginal title: Latent Performance Profiling of Large Language ModelsA preprint presents a framework that measures hidden activations in language models to reveal traits benchmarks miss.Added 23 Oct 2026
PreprintNot peer reviewedArtificial IntelligenceResearchers propose lifetime-aware KV cache placement to extend flash memory life in agent servingOriginal title: Lachesis: Lifetime-Aware KV Cache Placement for Agent Serving across HBM and High-Bandwidth FlashA preprint reports a placement layer that sorts AI agent memory by lifetime, extending flash memory's usable life over a simple baseline.Jaehoon Yang et al. · Added 23 Oct 2026
PreprintNot peer reviewedFrom HuaweiArtificial IntelligencePreprint explores how intermediate retrieval rewards improve training of search agentsOriginal title: Beyond Outcome Rewards: Constructing and Assigning Retrieval Credit for Search AgentsA preprint reports that rewarding intermediate retrieval steps, not just final answers, improves search-agent training across seven QA benchmarks.Added 23 Oct 2026
PreprintNot peer reviewedQuantum ComputingPreprint reports faster algorithms to localise logical qubit information under photon lossOriginal title: Logical information localisation in stabiliser codes via single-qubit measurementsA preprint proposes two algorithms that speed up finding where to read out logical information in stabiliser codes hit by qubit loss.Jelena Mackeprang et al. · Added 23 Oct 2026
PreprintNot peer reviewedFrom Quantum MotionQuantum ComputingPreprint evaluates layer codes as active quantum memories under circuit noiseOriginal title: Layer codes as quantum memories: syndrome extraction, thresholds and idle robustnessA preprint designs a syndrome extraction scheme for layer codes and finds they tolerate longer idle times than surface codes, but at higher qubit and gate cost.Added 23 Oct 2026
PreprintNot peer reviewedArtificial IntelligenceA preprint links LLM reasoning to pattern recognition via a shared graph structureOriginal title: The Dichotomy Between Pattern Recognition and Step-by-Step ReasoningResearchers propose that step-by-step reasoning and pattern recognition in LLMs sit on one spectrum, governed by how much context matters.Amrut Nadgir et al. · Added 23 Oct 2026
PreprintNot peer reviewedQuantum ComputingResearchers report noisy 1D quantum circuits offer no parallel speed-up over classical onesOriginal title: Parallel classical simulation of noisy shallow circuits: no quantum advantage in 1DA preprint finds that noisy one-dimensional shallow quantum circuits can be matched by parallel classical algorithms, unlike higher-dimensional cases.Robert Koenig et al. · Added 23 Oct 2026
PreprintNot peer reviewedQuantum ComputingA preprint reports an RL system that synthesises compact quantum state-preparation circuitsOriginal title: TATVA: A Reinforcement Learning Framework for Quantum Circuit SynthesisA preprint describes TATVA, a dual-agent reinforcement learning system that builds high-fidelity quantum circuits up to five qubits.Om Bhamare et al. · Added 23 Oct 2026
