PreprintNot peer reviewedArtificial IntelligencePreprint proposes dynamic budget allocation for testing when LLMs jailbreak or failOriginal title: How Many Iterations to Jailbreak? Dynamic Budget Allocation for Multi-Turn LLM EvaluationResearchers report a method that adaptively spends a fixed interaction budget to more reliably bound how many turns it takes for an LLM to jailbreak or complete a task.Shai Feldman et al. · Added 1 Nov 2026
PreprintNot peer reviewedArtificial IntelligenceResearchers propose attack-chain approach to catch email prompt injection attemptsOriginal title: Prompt Injection Detection for Email Agents Through Attack Chain ModelingA preprint models indirect prompt injection in email agents as a multi-stage attack chain rather than a single text classification task.Ahmad Hashmi et al. · Added 1 Nov 2026
PreprintNot peer reviewedFrom IntuitArtificial IntelligenceResearchers report offline fine-tuning method that treats feedback scores as goalsOriginal title: Goal-Conditioned Supervised Learning for LLM Fine-TuningA preprint proposes training LLMs via supervised learning to exceed quality thresholds, reportedly beating standard offline fine-tuning methods.Added 1 Nov 2026
PreprintNot peer reviewedFrom EnhansArtificial IntelligenceResearchers report multi-agent prompt optimizer outperforms prior methods on HelpSteer benchmarksOriginal title: MA-SAPO: Multi-Agent Reasoning for Score-Aware Prompt OptimizationA preprint describes MA-SAPO, a multi-agent system that turns evaluation scores into reusable reasoning assets to guide prompt edits.Added 1 Nov 2026
PreprintNot peer reviewedArtificial IntelligencePreprint proposes routing questions to specialist medical LLMs for better QA accuracyOriginal title: MedRouter: Demystifying Knowledge Differences Across Medical LLMs for Routing-Based ReasoningA preprint reports that routing medical questions to specialist LLMs and combining their answers outperforms picking a single best model.Lang Cao et al. · Added 1 Nov 2026
PreprintNot peer reviewedArtificial IntelligencePreprint proposes combining prompt evolution with RL to fix stuck reward signals in LLM reasoningOriginal title: P^2O: Joint Policy and Prompt OptimizationA preprint reports a method joining prompt evolution and policy updates to tackle vanishing reward signals on hard reasoning problems.Xinyu Lu et al. · Added 1 Nov 2026
PreprintNot peer reviewedFrom NVIDIAArtificial IntelligenceResearchers report a tuning-free method to stretch LLM context windows without retrainingOriginal title: Jet-Long: Efficient Long-Context Extension with Dynamic Bifocal RoPEA preprint describes Jet-Long, a zero-shot context-extension technique that reportedly outperforms existing baselines while keeping most of FlashAttention-3's speed.Added 1 Nov 2026
PreprintNot peer reviewedArtificial IntelligencePreprint reports narrow fine-tuning can misalign vision-language models broadlyOriginal title: Narrow Multimodal Fine-Tuning Can Induce Emergent MisalignmentA preprint reports that narrow multimodal fine-tuning can produce broad, unrelated misaligned behaviour across vision-language models.Shunchang Liu et al. · Added 1 Nov 2026
PreprintNot peer reviewedFrom ForSight RoboticsArtificial IntelligenceResearchers report using vision-language models to prioritise RL replay buffer experiencesOriginal title: VLM-Guided Experience ReplayA preprint reports that scoring replay buffer clips with a frozen vision-language model boosts reinforcement learning success rates and sample efficiency.Added 1 Nov 2026
PreprintNot peer reviewedArtificial IntelligenceA preprint proposes a fairness-aware training method for multi-step AI agentsOriginal title: Agentic Multi-Turn Reasoning: A Fairness ApproachResearchers describe Phi-MPO, a preference-learning method aimed at improving long multi-turn AI agent reasoning and reducing data imbalance effects.Thanh-Dat Truong et al. · Added 1 Nov 2026
PreprintNot peer reviewedArtificial IntelligencePreprint explores compact per-turn memory instead of full chat history for LLM agentsOriginal title: Continuous Context ManagementA preprint reports that updating a short memory every turn cuts context size but affects task success differently across models.William Hoy et al. · Added 1 Nov 2026
PreprintNot peer reviewedArtificial IntelligenceA preprint surveys how RAG and reasoning methods curb LLM hallucinationsOriginal title: Mitigating Hallucination in Large Language Models: A Capability-Oriented Survey on RAG, Reasoning, and Agentic SystemsA preprint proposes a framework linking hallucination types to retrieval, reasoning and agentic mitigation methods.Yihan Li et al. · Added 1 Nov 2026
PreprintNot peer reviewedFrom ByteDanceArtificial IntelligenceA preprint reports a likelihood-free RL method for diffusion language modelsOriginal title: LFPO: Likelihood-Free Policy Optimization for Masked Diffusion ModelsResearchers describe LFPO, a training approach for diffusion language models that avoids estimating intractable sequence likelihoods during reinforcement learning.Added 1 Nov 2026
PreprintNot peer reviewedQuantum ComputingResearchers report FALQON with an XY mixer improves quantum graph colouringOriginal title: Solving Graph Coloring Problems Using Feedback-Based Algorithm for Quantum OptimizationA preprint reports that adding an XY mixer to a feedback-based quantum optimisation algorithm improves graph colouring success over the standard approach.Yuika Kawatomi et al. · Added 1 Nov 2026
PreprintNot peer reviewedQuantum ComputingPreprint reports exponential quantum speed-up for testing Fourier dimensionOriginal title: Exponential Quantum Advantage in Testing Fourier DimensionalityA preprint reports a quantum algorithm that tests Fourier dimensionality far faster than any classical method can match.Kenny Chen · Added 1 Nov 2026
PreprintNot peer reviewedArtificial IntelligenceA preprint proposes a diffusion-based reward model for LLM alignmentOriginal title: Diffusion Reward ModelsResearchers report a diffusion reward head that models reward distributions instead of a single score, matching or beating baselines on five benchmarks.Xiangyang Wang et al. · Added 1 Nov 2026
PreprintNot peer reviewedFrom GyriQAIQuantum ComputingPreprint finds quantum calibration histograms cannot reveal the sign of rotation errorsOriginal title: Identifying the Sign of Coherent Over-Rotations with Logarithmically Many Pauli SettingsA preprint reports that a single calibration measurement can never tell whether a quantum gate over-rotates or under-rotates.Added 1 Nov 2026
PreprintNot peer reviewedFrom Qualcomm AI ResearchArtificial IntelligencePreprint proposes looped transformer design that keeps memory constant as reasoning depth growsOriginal title: Memory-Efficient Looped Transformer: Decoupling Compute from Memory in Looped Language ModelsA preprint describes MELT, a looped transformer that shares one KV cache across reasoning loops to avoid linear memory growth.Added 1 Nov 2026
PreprintNot peer reviewedFrom Alibaba GroupArtificial IntelligenceResearchers report faster on-device LLM responses via KV cache reuse on mobile NPUsOriginal title: Dynamic Flow, Static Graph: KV Cache Reuse for Efficient LLM Serving on Mobile NPUsA preprint describes a compute-storage system that reuses KV cache on mobile NPUs to cut first-token latency.Added 1 Nov 2026
PreprintNot peer reviewedQuantum ComputingPreprint proposes compressed query method for simulating time-varying Lindblad dynamicsOriginal title: Causal Query Compression for Lindblad Dynamics: Optimal Queries and Nearly Linear Local SimulationA preprint reports new query and gate bounds for simulating time-dependent open quantum systems using causal query compression.Jacob Kitchen · Added 1 Nov 2026
