PreprintNot peer reviewedArtificial IntelligenceResearchers report a benchmark for testing LLM agents on geospatial API tasksOriginal title: GeoNatureAgent (GNA): A Framework and Benchmark for Pre-Production Evaluation of Tool-Using Agents on Geospatial and Environmental TasksA preprint introduces a geospatial agent benchmark, finding that even the best large language model struggles with strict end-to-end tool use.Gabriel Diaz-Ireland et al. · Added 9 Nov 2026
PreprintNot peer reviewedArtificial IntelligencePreprint proposes graph-based memory architecture for LLM long-term dialogueOriginal title: From Retrieval to Reconstruction: Constructing Evolvable Cognitive Memory for Long-Term DialogueA preprint introduces CogMem, a schema-based memory system that separates opinions from facts to improve long-term dialogue reasoning.Zirui Liao et al. · Added 9 Nov 2026
PreprintNot peer reviewedFrom SalesforceArtificial IntelligenceResearchers propose turning retrieved text into model memory instead of live lookupsOriginal title: From Lookups to Lessons: Turning Retrieved Knowledge into Parametric MemoryA preprint describes ResMem, which trains a parametric memory from retrieved text to cut storage while preserving correct answers.Added 9 Nov 2026
PreprintNot peer reviewedFrom GoogleArtificial IntelligenceResearchers trace how state-controlled media spreads through AI training dataOriginal title: The World as Viewed by 136 Countries: An Open, Curated, Annotated, and Multilingual Dataset of 118 Million State Media ArticlesA new dataset tracks state media's rising share of web data used to train and ground AI language models.Added 9 Nov 2026
PreprintNot peer reviewedQuantum ComputingA preprint reports shallow-circuit method for measuring quantum energy gaps on noisy hardwareOriginal title: Low-Resource Quantum Energy Gap Estimation via RandomizationResearchers combine two randomised quantum techniques to estimate energy gaps using shallower circuits, reporting better noise robustness on IBM hardware.Hugo Pages et al. · Added 9 Nov 2026
PreprintNot peer reviewedArtificial IntelligencePreprint proposes navigator model to pick replay data against LLM forgettingOriginal title: NADS: Navigator-Guided Data Selection for Mitigating Catastrophic Forgetting in Fine-TuningA preprint describes NADS, a method using a drifted reference model to choose synthetic data that helps fine-tuned LLMs keep prior skills.Jianhao Zhang et al. · Added 9 Nov 2026
PreprintNot peer reviewedFrom Waymo / Adobe Research / Bosch / NVIDIAArtificial IntelligenceSurvey maps how generative AI could reshape autonomous driving researchOriginal title: Generative AI for Autonomous Driving: Frontiers and OpportunitiesA preprint surveys how generative models like diffusion and LLMs are being applied across the autonomous driving technology stack.Added 9 Nov 2026
PreprintNot peer reviewedFrom Embedded CustomsQuantum ComputingResearchers describe SpinControl, control software for spin-qubit quantum devicesOriginal title: SpinControl: Control Software for Prototyping and Benchmarking of Spin-Qubit Devices and Measurement ProtocolsA preprint describes SpinControl, a Python framework for tuning, calibrating and benchmarking semiconductor spin-qubit quantum computers.Added 9 Nov 2026
PreprintNot peer reviewedFrom MicrosoftArtificial IntelligenceA preprint describes a multi-agent system for geospatial disaster analytics outperforming coding agentsOriginal title: GeoFaham: Domain-Specialized Multi-Agent Geospatial Analytics for Disaster ResponseResearchers report a specialised multi-agent system beat general coding agents on a 40-task disaster-analytics benchmark while using far fewer tokens.Added 9 Nov 2026
PreprintNot peer reviewedFrom Patronus AIArtificial IntelligencePreprint finds masked diffusion models outperform larger autoregressive models as world simulatorsOriginal title: Masked Diffusion Language Models are Strong and Steerable Text-Based World Models for Agentic RLA preprint reports that masked diffusion language models simulate text-based agent environments more faithfully than much larger autoregressive LLMs.Added 9 Nov 2026
PreprintNot peer reviewedQuantum ComputingResearchers report post-quantum TLS can beat classical crypto on tiny IoT chipsOriginal title: Testing TLS 1.3 PQC on constrained devices and microcontrollersA preprint benchmarking wolfSSL finds ML-KEM-512 handshakes often faster and more efficient than X25519 on constrained microcontrollers.Olivier Gillot et al. · Added 9 Nov 2026
PreprintNot peer reviewedFrom MeituanArtificial IntelligenceResearchers report a scaling law predicting VLM performance from text-only LLM scoresOriginal title: What Transfers from Text to Vision? Capability Scaling Laws and Transfer Dynamics for VLMsA preprint proposes a scaling law that predicts vision-language model accuracy from a backbone's textual benchmark scores, tested on over 150 trained VLMs.Added 9 Nov 2026
Conference paperReview status unknownArtificial IntelligenceResearchers propose agent-based framework to counter OWASP’s top LLM security risksOriginal title: Mitigating the OWASP Top 10 For Large Language Models Applications using Intelligent AgentsA conference paper outlines an AI-agent framework meant to detect and counter the OWASP Top 10 risks for LLM applications.Mohammad Fasha et al. · Added 9 Nov 2026 · Released Feb 2024
Journal articleReview status unknownQuantum ComputingReview maps progress toward hour- and minute-scale quantum memories in rare-earth crystalsOriginal title: Long-lived quantum memories with rare-earth ions doped in crystalsA review surveys rare-earth-ion crystals as quantum memory platforms, tracking spin coherence, light storage and single-photon storage lifetimes.Yu-Yu Sa et al. · Added 9 Nov 2026
PreprintNot peer reviewedFrom Microsoft AIArtificial IntelligenceOffline trajectory method rivals online RL for training code-generation LLMsOriginal title: COBALT: Contextual Bandit Learning with Offline Trajectories for Multi-Turn Code GenerationA preprint reports an offline bandit-style training method that matches online reinforcement learning for multi-turn code generation while cutting rollout costs.Added 9 Nov 2026
Journal articleReview status unknownQuantum ComputingNew classical sampling method speeds up simulation of Clifford+T circuitsOriginal title: Classical Clifford+T Sampling without Computing MarginalsA paper introduces T-by-T sampling, an exact classical sampling method whose cost depends only on T-count, not surrounding Clifford operations.Mark Koch · Added 9 Nov 2026
PreprintNot peer reviewedArtificial IntelligenceA preprint links positional encoding and depth to limits on LLM reasoning generalisationOriginal title: A Measure-Theoretic Analysis of Reasoning in Transformers: Structural Generalization and Approximation LimitsA preprint develops a transport-theoretic framework tying position encoding and layer depth to how well Transformers generalise reasoning to new search structures.Yuyang Zhang et al. · Added 9 Nov 2026
PreprintNot peer reviewedArtificial IntelligenceA preprint proposes pooling Adam’s optimizer memory for LLM trainingOriginal title: AdamPM: Memory-Efficient LLM Optimization via Moment PoolingResearchers report a modified Adam optimizer that pools second-moment values to cut memory use while keeping training performance similar.Xiaowei Ji et al. · Added 9 Nov 2026
Journal articleReview status unknownQuantum ComputingTheory study models charge-noise limits and fixes for SAGE spin qubitsOriginal title: Singlet-only always-on gapless exchange (SAGE) spin qubits: Charge noise effects and two-qubit gatesResearchers model how charge noise affects SAGE spin qubits and report that refocusing pulses can greatly extend coherence and gate fidelity.Nathan L. Foulk et al. · Added 9 Nov 2026
PreprintNot peer reviewedArtificial IntelligenceA preprint links power sampling, self-reward RL and self-distillation in LLMsOriginal title: Power Distribution Bridges Sampling, Self-Reward RL, and Self-DistillationResearchers report that a single power distribution connects sampling, self-reward RL and distillation, offering a cheaper alternative to inference-time sampling.Akiyoshi Tomihari et al. · Added 9 Nov 2026
