PreprintNot peer reviewedArtificial IntelligenceA preprint reports LLMs cling to internal concepts despite clearer promptsOriginal title: On the Limits of LLM Adaptability: Impact of Model-Internalized Priors on Annotation Task PerformanceA preprint finds language models rely on built-in notions of toxicity that prompting struggles to override.Etienne Casanova et al. · Added 6 Oct 2026
PreprintNot peer reviewedArtificial IntelligenceA preprint benchmark compares KV-cache reuse methods across models and contextsOriginal title: KVShareArena: KV-Cache Reuse Across Contexts and Model CheckpointsA new benchmark called KVShareArena tests how well KV-cache repair methods hold up when context or model weights change.Xi Shi et al. · Added 6 Oct 2026
PreprintNot peer reviewedArtificial IntelligenceResearchers propose TRACE fine-tuning to handle knowledge conflicts in RAG systemsOriginal title: Parameters vs. Context: TRACE Fine-Tuning for Robust Retrieval-Augmented GenerationA preprint presents TRACE, a fine-tuning method using debate traces to help RAG models choose between retrieved context and internal knowledge.Zhengchen Huang et al. · Added 6 Oct 2026
PreprintNot peer reviewedQuantum ComputingPreprint describes a self-correcting quantum computer built from local, translation-invariant dynamicsOriginal title: Quantum Memory and Autonomous Computation in Two DimensionsA preprint outlines a two-dimensional dissipative scheme that autonomously corrects errors and runs fault-tolerant quantum computation without measurements.Gesa Dünnweber et al. · Added 6 Oct 2026
PreprintNot peer reviewedArtificial IntelligenceA preprint reports LLMs miscoordinate in 38% of high-stakes multi-agent safety testsOriginal title: GT-HarmBench: Benchmarking AI Safety Risks Through the Lens of Game TheoryA new benchmark finds frontier language models often fail to pick socially safe actions in game-theoretic safety scenarios.Pepijn Cobben et al. · Added 6 Oct 2026
PreprintNot peer reviewedArtificial IntelligencePreprint finds LLMs can solve every math sub-step yet still fail to combine themOriginal title: Solving Every Step Is Not Enough: Milestone Oracles Reveal a Composition Gap in LLM Math ReasoningA preprint reports that giving models step-by-step milestones often fails to fix maths errors, pointing to a composition gap.Zhuohan Wang et al. · Added 6 Oct 2026
Conference paperReview status unknownArtificial IntelligenceStudy finds LLMs can often guess which AI model they are talking toOriginal title: Agent-to-Agent Theory of Mind: Testing Interlocutor Awareness among Large Language ModelsResearchers report that large language models can identify their conversational partners, and that this awareness creates both collaboration gains and new safety risks.Younwoo Choi et al. · Added 6 Oct 2026 · Released Jan 2025
PreprintNot peer reviewedQuantum ComputingPreprint explores hybrid error correction for linking quantum processors over photonic linksOriginal title: Loss-tolerant distributed lattice surgery using fusion networksA preprint examines hybrid measurement- and circuit-based schemes for connecting quantum processors via lossy photonic links.Felix Burt et al. · Added 6 Oct 2026
PreprintNot peer reviewedQuantum ComputingResearchers report adaptive single-copy measurements can match two-copy stabilizer learningOriginal title: Adaptivity is all you need: Optimal stabilizer learning using just single-copy measurementsA preprint reports that adaptive single-copy measurements learn stabilizer states as efficiently as two-copy Bell sampling.L. Bittel et al. · Added 6 Oct 2026
PreprintNot peer reviewedArtificial IntelligencePreprint reports targeted preference training cuts unsupported answers in a vision-language modelOriginal title: Reducing Hallucination in Multimodal Large Language Models through Hard Grounding Preference SupervisionA preprint describes refining a multimodal model with hard grounding preference pairs, reporting gains on benchmarks and judged pairwise comparisons.Qinwu Xu · Added 6 Oct 2026
PreprintNot peer reviewedArtificial IntelligencePreprint proposes calibrated importance sampling to fix LLM RL training-inference mismatchOriginal title: Rethinking Training-Inference Mismatch in LLM Reinforcement Learning: Where It Arises and How to Correct ItA preprint reports a new correction, CIS, for mismatches between training and inference engines in reinforcement learning for large language models.Tianrun Yu et al. · Added 6 Oct 2026
PreprintNot peer reviewedFrom NVIDIAArtificial IntelligenceResearchers report offline distillation method matches on-policy teacher training at lower costOriginal title: Lightning OPD: Efficient Post-Training for Large Reasoning Models with Offline On-Policy DistillationA preprint describes Lightning OPD, an offline distillation method the authors say matches standard on-policy distillation while using far less compute.Added 6 Oct 2026
PreprintNot peer reviewedQuantum ComputingPreprint reports quantum memory edge for a polynomial-fitting problem in streaming settingOriginal title: Exponential quantum advantages for decoded quantum interferometry in the streaming settingA preprint reports that an adapted quantum algorithm beats classical streaming methods on a polynomial-fitting problem using far less memory.Kewen Wu et al. · Added 6 Oct 2026
PreprintNot peer reviewedArtificial IntelligencePreprint describes TokenCake, a cache-aware serving system for multi-agent LLM workloadsOriginal title: TokenCake: A KV-Cache-centric Serving Framework for LLM-based Multi-Agent ApplicationsA preprint reports that TokenCake improves GPU memory handling and latency for multi-agent LLM serving by managing idle and contended caches.Zhuohang Bian et al. · Added 6 Oct 2026
PreprintNot peer reviewedQuantum ComputingExperiment tests Grover’s algorithm for detecting unknown-frequency signalsOriginal title: Experimental quantum-computing-enhanced sensing using Grover's algorithmResearchers built a small superconducting qubit-cavity device to test whether Grover's algorithm can improve signal detection over wide bandwidths.Mathieu Ouellet et al. · Added 6 Oct 2026
PreprintNot peer reviewedFrom MeituanArtificial IntelligenceTGRL turns rollout temperature into a training signal for LLM reasoning, authors reportOriginal title: TGRL: Temperature-Grouped Reinforcement Learning for Efficient Exploration in LLMsA preprint proposes TGRL, which converts temperature-based rollout diversity into token-level training credit for reinforcement learning with verifiable rewards.Added 6 Oct 2026
PreprintNot peer reviewedArtificial IntelligenceA preprint reports a test-time training method for code LLMs robust to noisy promptsOriginal title: Noisy Test-Time Reinforcement Learning for Code LLMsResearchers propose NTRL-Code, a label-free test-time reinforcement learning method that helps code LLMs cope with noisy, error-prone prompts.Xikai Yang et al. · Added 6 Oct 2026
PreprintNot peer reviewedQuantum ComputingPreprint reports constant-overhead method for fault-tolerant quantum state preparationOriginal title: Fault-tolerant interfaces for quantum LDPC codesA preprint reports a fault-tolerant scheme for preparing quantum states that needs only constant, rather than growing, qubit overhead.Matthias Christandl et al. · Added 6 Oct 2026
PreprintNot peer reviewedArtificial IntelligenceNew benchmark finds LLM agents still struggle with power-grid analysis tasksOriginal title: PowerBench: A Benchmark for Agentic Retrieval and Reasoning in Power SystemsA preprint introduces PowerBench, a synthetic power-system dataset and benchmark, and reports that top LLM agents still fall short on multi-step retrieval and reasoning tasks.Xijing Wang et al. · Added 6 Oct 2026
PreprintNot peer reviewedArtificial IntelligenceA preprint reports a self-distillation method that targets only flawed reasoning steps in LLMsOriginal title: Beyond Imitation: Reflective On-Policy Self-Distillation for LLM ReasoningResearchers propose ROSD, which corrects only the erroneous part of an LLM's reasoning trace instead of imitating a full reference solution.Ziqi Zhao et al. · Added 6 Oct 2026
