PreprintNot peer reviewedArtificial IntelligenceReview maps environmental costs of generative and agentic AI, authors reportOriginal title: Environmental Impact of Generative and Agentic AI: An in-Depth Analysis and Green SolutionsA preprint reviews energy, carbon, water and e-waste impacts across the AI lifecycle, flagging agentic workflows as a major multiplier.Abderaouf Bahi et al. · Added 1 Nov 2026
PreprintNot peer reviewedFrom NAVER Cloud, Toss, A2SYSArtificial IntelligenceResearchers propose shared prefill module to cut redundancy in multi-model LLM servingOriginal title: PrefillShare: A Shared Prefill Module for KV Reuse in Multi-LLM Disaggregated ServingA preprint describes PrefillShare, which lets multiple fine-tuned LLMs reuse one prefill computation and KV cache, cutting latency and boosting throughput.Added 1 Nov 2026
PreprintNot peer reviewedQuantum ComputingResearchers report reinforcement learning speeds up dissipative quantum state preparationOriginal title: Adaptive Dissipative State Preparation through Reinforcement LearningA preprint reports a reinforcement learning method that picks bath settings on the fly to prepare quantum ground states faster.Nathan M. Myers et al. · Added 1 Nov 2026
PreprintNot peer reviewedArtificial IntelligencePreprint measures energy costs of 25 open LLMs for code completionOriginal title: Green AI: Cost of LLM-Based Code CompletionA preprint reports that energy use in LLM code completion depends on task type, with smaller quantized models often matching larger ones efficiently.Negar Alizadeh et al. · Added 1 Nov 2026
PreprintNot peer reviewedArtificial IntelligenceResearchers propose unlearning for agent action trajectories, not just factsOriginal title: Trajectory Unlearning on LLM-based AgentsA preprint introduces trajectory-level unlearning for LLM agents and a method called GiRPO that forgets bad action sequences while keeping task performance.Yingdan Shi et al. · Added 1 Nov 2026
PreprintNot peer reviewedArtificial IntelligenceResearchers propose Theory of Scene to fix coordination failures in homogeneous LLM agent teamsOriginal title: Theory of Scene: Breaking the Symmetry Trap in Multi-Agent LLM CoordinationA preprint reports a training-free reasoning method that helps identical LLM agents split or combine tasks without talking to each other.Liangqi Yuan et al. · Added 1 Nov 2026
PreprintNot peer reviewedQuantum ComputingA preprint maps complexity limits on quantum state preparation for approximate MaxCutOriginal title: Complexity Barriers to State Preparation in Quantum Approximate OptimizationA preprint reports that quantum methods for approximate MaxCut face a complexity barrier tied to the gain above random guessing, not just approximation ratio.Stuart Hadfield · Added 1 Nov 2026
PreprintNot peer reviewedArtificial IntelligenceA preprint reports personalized reward models miss preference signals in contextOriginal title: Using Context Is Not Enough: Test-Time Training for Personalized Reward ModelingA preprint proposes test-time weight updates to help reward models better use labelled preference pairs from user history.Bohao Wang et al. · Added 1 Nov 2026
PreprintNot peer reviewedFrom PsiQuantumQuantum ComputingPreprint proposes a cycle-level scheduler for Active Volume quantum architecturesOriginal title: A Scalable, Optimized Scheduler for the Active Volume ArchitectureA preprint reports a scheduler that tracks reactions and stale states to sharpen resource estimates for Active Volume quantum computers.Added 1 Nov 2026
PreprintNot peer reviewedFrom QuantinuumQuantum ComputingResearchers trial a shared workflow system linking a supercomputer to two quantum computersOriginal title: Quantum-HPC Workflows Across Multiple Quantum Computing Platforms: Two Case StudiesA preprint describes running two quantum-HPC case studies on Fugaku with Quantinuum Reimei and IBM's ibm_kobe using the Tierkreis workflow tool.Added 1 Nov 2026
PreprintNot peer reviewedQuantum ComputingResearchers find classical reductions often fail on dense Rydberg-native optimisation graphsOriginal title: Reducibility of native weighted graphs on Rydberg ArraysA preprint reports that dense unit-disk graphs for Rydberg quantum processors often resist classical simplification, especially with longer-range connectivity.J. Kombe et al. · Added 1 Nov 2026
PreprintNot peer reviewedQuantum ComputingA preprint links quantum many-body chaos to a fractal operator cascadeOriginal title: Quantum many-body operator cascade as a route to chaosA preprint proposes that quantum many-body chaos arises from local operators drifting toward non-local fractal structures, aiding classical simulation.Urban Duh et al. · Added 1 Nov 2026
PreprintNot peer reviewedQuantum ComputingPreprint proposes q-derivative framework to curb leakage in superconducting qubitsOriginal title: A Novel $q$-Derivative Framework with Applications to $q$-Deformed Thermodynamics and Leakage Suppression in Superconducting QubitsA preprint outlines a new q-deformed derivative that extends DRAG-style pulse shaping to reduce leakage errors in transmon qubits.André A. A. Marinho et al. · Added 1 Nov 2026
PreprintNot peer reviewedFrom TencentArtificial IntelligenceA preprint reports hypergraph method for linking retrieved evidence in LLM reasoningOriginal title: HyperReCo: Retrieving and Connecting Evidence with Hypergraph Neural Networks for LLM Multi-hop ReasoningResearchers describe HyperReCo, a hypergraph neural network that retrieves and explicitly links multi-hop evidence for LLM question answering.Added 1 Nov 2026
PreprintNot peer reviewedArtificial IntelligencePreprint proposes framework for detecting self-organisation in LLM agent societiesOriginal title: Population Physics, Population Problems: Safety and Emergence in LLM SocietiesA preprint introduces a statistical framework to detect unplanned collective behaviour across simulated LLM societies without reading agent language.Adrian de Wynter · Added 1 Nov 2026
PreprintNot peer reviewedFrom Microsoft ResearchArtificial IntelligenceA preprint reports RL-trained self-refinement lets small LLMs rival 32B-235B models on codingOriginal title: RefineRL: Advancing Competitive Programming with Self-Refinement Reinforcement LearningA preprint describes RefineRL, an RL method that teaches compact 4B language models to skeptically refine their own competitive-programming solutions.Added 1 Nov 2026
PreprintNot peer reviewedArtificial IntelligenceResearchers propose streaming benchmark for AI reading long ambulatory ECGsOriginal title: ECG-Scroll: A Long-Horizon, Streaming Benchmark and Agent Environment for Interpretation of Ambulatory ElectrocardiogramsA preprint introduces a streaming benchmark testing whether language-model agents can spot rare cardiac events in day-long ECG recordings as they unfold.Haitao Li et al. · Added 1 Nov 2026
PreprintNot peer reviewedQuantum ComputingResearchers report tight quantum time-space limits for collision finding under label symmetryOriginal title: Tight Time-Space Lower Bounds for Collision Finding and Element Distinctness under Label SymmetryA preprint proves optimal query-space tradeoffs for quantum collision finding and Element Distinctness, but only for label-symmetric algorithms.Frédéric Magniez et al. · Added 1 Nov 2026
PreprintNot peer reviewedFrom AmazonArtificial IntelligencePreprint proposes letting LLMs judge their own training curriculum during fine-tuningOriginal title: Internalizing Curriculum Judgment for LLM Reinforcement Fine-TuningA preprint reports a method, METIS, where a language model predicts which prompts will teach it the most, speeding up reinforcement fine-tuning.Added 1 Nov 2026
PreprintNot peer reviewedQuantum ComputingA preprint reports quantum pointer records can form via an intermediate apparatus, not just direct contactOriginal title: Quantum Darwinism through apparatus-mediated environmental recordingA preprint compares two quantum Darwinism models and finds apparatus-mediated environments can preserve pointer information as well as direct ones.Tran P.H Don et al. · Added 1 Nov 2026
