PreprintNot peer reviewedArtificial IntelligencePreprint proposes dependency graphs to give RL agents step-by-step creditOriginal title: Dependency-Aware Reward Shaping for Agentic Reinforcement LearningA preprint reports a reward-shaping method that tracks task prerequisites to assign step-level credit in agentic reinforcement learning.Ziyi Chen et al. · Added 7 Oct 2026
PreprintNot peer reviewedFrom BaiduArtificial IntelligenceResearchers propose highlight-then-summarize method to improve long-context LLM reasoningOriginal title: Highlight-Then-Summarize: Learning to Compress Evidence for Long-Context UnderstandingA preprint introduces H2S, a method that extracts evidence then summarises it before answering, reportedly boosting long-context benchmark scores.Added 7 Oct 2026
PreprintNot peer reviewedFrom QuEra ComputingQuantum ComputingNew method efficiently simulates fidelity of large non-Clifford quantum circuitsOriginal title: Efficient fidelity simulation of high-rate magic distillation circuitsA preprint presents classical algorithms to efficiently estimate fidelity of fault-tolerant circuits with many non-Clifford gates.Added 7 Oct 2026
PreprintNot peer reviewedArtificial IntelligencePreprint: cheap open-weight judge panels can often stand in for costly AI judgesOriginal title: RAIM: Robust Aggregation of Inexpensive Models for Hallucination DetectionA preprint reports that aggregating ten small open-weight language models can approach a frontier model's performance at a fraction of the cost for detecting hallucinations.Elia Onofri et al. · Added 7 Oct 2026
PreprintNot peer reviewedQuantum ComputingResearchers report quantum algorithm shortcut for simulating multi-exciton states in materialsOriginal title: Quasiparticle quantum simulation of materials with the Bethe-Salpeter equationA preprint reports a quasiparticle-based quantum algorithm that could sharply cut the computing cost of simulating multi-exciton states in semiconductors.Jielun Chen et al. · Added 7 Oct 2026
PreprintNot peer reviewedFrom IBMArtificial IntelligenceResearchers report belief queries help LLM agents act under uncertaintyOriginal title: Towards a Belief-Based World Model for LLM AgentsA preprint finds that letting language model agents query a world model's beliefs, not just simulate futures, improves decision-making under partial observability.Added 7 Oct 2026
PreprintNot peer reviewedArtificial IntelligenceA preprint proposes token-level advantage signals for training multimodal reasoning modelsOriginal title: Reinforcing Multimodal Reasoning via Token-Level Perception-Grounded Advantage EstimationResearchers report a method that scores individual tokens, not just whole answers, to guide reinforcement learning for multimodal reasoning.Zhihan Zhang et al. · Added 7 Oct 2026
Journal article✓ Peer reviewedQuantum ComputingStudy finds hollow-core fibre could reshape quantum repeater network designOriginal title: Quantum networking with advances in fiber technologyA peer-reviewed study reports that hollow-core fibre can substantially outperform standard silica fibre in simulated quantum repeater networks.Prateek Mantri et al. · Added 6 Oct 2026
PreprintNot peer reviewedFrom HuaweiArtificial IntelligenceTest-time method adapts LLM confidence calibration without labelled data, authors reportOriginal title: Test-time Calibration Learning for Large Language Model ReasoningA preprint proposes a label-free way to adjust an LLM's confidence estimates at test time using only its own generated answers.Added 6 Oct 2026
PreprintNot peer reviewedFrom GoogleQuantum ComputingPreprint proposes modular hyperbolic codes to cut quantum error correction overheadOriginal title: Low-Overhead Quantum Error Correction with Boundary-Connected Planar ModulesA preprint reports that boundary-linked planar modules built from hyperbolic surface and colour codes could sharply cut the qubit overhead needed for quantum error correction.Added 6 Oct 2026
PreprintNot peer reviewedArtificial IntelligenceMethod estimates hidden pre-training gradients to curb LLM forgetting during fine-tuningOriginal title: Estimating and Orthogonalizing Unknown Pre-training Gradients for Continual Fine-tuning of Large Language ModelsA preprint proposes generating pseudo pre-training data to estimate unknown gradients, helping LLMs retain general knowledge while learning new tasks.Bing Wang et al. · Added 6 Oct 2026
PreprintNot peer reviewedFrom IonQQuantum ComputingPreprint: trapped-ion quantum computer recovers magnet’s spin spectra with compressed circuitsOriginal title: Quantum simulation of field-tunable spin spectroscopy of the quantum magnet Cs2CoCl4 on a trapped-ion quantum computerResearchers report simulating a 36-site quantum magnet model on IonQ hardware, matching classical and neutron-scattering benchmarks using compact circuits.Added 6 Oct 2026
PreprintNot peer reviewedArtificial IntelligenceA preprint reports an RL framework to help AI agents find more, not just one, correct answersOriginal title: SPADER: Step-wise Peer Advantage with Diversity-Aware Exploration Rewards for Multi-Answer Question AnsweringResearchers describe SPADER, a reinforcement learning method aimed at improving tool-using AI agents on questions with many correct answers.Qiming Shi et al. · Added 6 Oct 2026
PreprintNot peer reviewedArtificial IntelligenceA preprint reports concept-graph distillation improves LLM-to-student training efficiencyOriginal title: Distilling LLM Reasoning into Graph of Concept PredictorsResearchers propose mirroring an LLM's reasoning steps as a graph of concept predictors to train cheaper student classifiers with less labelling.Ziyang Yu et al. · Added 6 Oct 2026
PreprintNot peer reviewedQuantum ComputingResearchers report quantum-dot photon source supports entanglement-swapped key distributionOriginal title: Quantum Key Distribution with Entanglement-Swapped Photons from a Quantum EmitterA preprint reports secure key exchange using entanglement-swapped photons from a quantum dot source, a step towards quantum repeaters.Michele B. Rota et al. · Added 6 Oct 2026
PreprintNot peer reviewedArtificial IntelligenceA preprint reports LLMs struggle to clarify ambiguous coding requirementsOriginal title: ClarifyCodeBench: Evaluating LLMs on Clarifying Ambiguous Requirements for Code GenerationA new benchmark finds that even strong code-generating LLMs often fail to ask the right questions when requirements are unclear.Zheng Fang et al. · Added 6 Oct 2026
PreprintNot peer reviewedArtificial IntelligenceA preprint links RLVR training collapse to loss of reasoning strategy diversityOriginal title: All Work And No Play Makes Jack a Dull Boy: Understanding and Preventing Catastrophic Strategy Collapse in RLVRResearchers propose a theory and fix for sudden accuracy drops during RLVR fine-tuning of reasoning LLMs.Qiyuan Huang et al. · Added 6 Oct 2026
PreprintNot peer reviewedArtificial IntelligenceA preprint reports LLMs often misfire when recalling well-known algorithms, not just inventing new onesOriginal title: Are you Synthesizing or Recalling? Evaluating LLMs on Algorithmic Code RetrievalA preprint proposes testing whether LLMs can faithfully reproduce known algorithms, finding frequent silent errors across languages.Nickil Maveli et al. · Added 6 Oct 2026
PreprintNot peer reviewedFrom China Mobile Internet CompanyArtificial IntelligenceA preprint reports faster on-device LLM inference for multi-agent systems on edge chipsOriginal title: EdgeAgent: Orchestrating On-Device LLM inference for End-User Multi-Agent Systems on CPU-GPU Unified Memory ArchitecturesResearchers describe EdgeAgent, a system that speeds up on-device LLM inference for multi-agent workloads on CPU-GPU unified memory chips.Added 6 Oct 2026
PreprintNot peer reviewedQuantum ComputingA preprint proposes judging noisy quantum computers by recoverable information, not perfect statesOriginal title: Recoverable Quantum Computation: An Information-Centric Paradigm for Quantum Computing with ErrorsA single-author preprint outlines a framework for deciding when noisy quantum computers can still give useful answers, without needing full error correction.Shengwang Du · Added 6 Oct 2026
