Key papers

• When the Chain of Thought Knows Better: Failure Modes in Multi-Turn Reasoning Models (2026)
  Sai Kartheek Reddy Kasu et al.
  5.82
• K-Forcing: Joint Next-K-Token Decoding via Push-Forward Language Modeling (2026)
  Zhiwei Tang et al.
  5.82
• TSAI-MetaFraud: A Benchmark Dataset for Financial Fraud Transaction and Behavioral Risk Detection in Metaverse Ecosystems (2026)
  Refat Ishrak Hemel et al.
  5.49
• From Confident Closing to Silent Failure: Characterizing False Success in LLM Agents (2026)
  Laksh Advani
  5.44
• Efficient AI-Inspired Reduction of Feynman Integrals via Tube Seeding (2026)
  Justin Berman et al.
  5.44
• The Binary Tree Mechanism is Optimal for Approximate Differentially Private Continual Counting (2026)
  Konstantina Bairaktari et al.
  5.01
• Unveiling the Non-Monotonic Effect of Privacy on Generalization under Byzantine Robustness (2026)
  Thomas Boudou et al.
  5.01
• RaMark: Radioactive Watermarking for Generated Tabular Data (2026)
  Xin Che et al.
  5.01
• Recovering Clinical Utility Under Differential Privacy: Empirical Validation of Adaptive Federated Aggregation on Heterogeneous Cardiovascular Datasets (2026)
  Rodrigo Tertulino et al.
  5.01
• End-to-End Differential Privacy in Training Deep Neural Network Classifiers (2026)
  Huaiyuan Rao et al.
  5.01
• Near-Optimal Decentralized Stochastic Convex Optimization over Networks (2026)
  Nitai Kluger et al.
  4.95
• Express Language Modeling (2026)
  Albert Gong et al.
  4.95
• Direct Preference Optimization for Chatbot Fine-Tuning: An Empirical Study (2026)
  Dezhi Yu et al.
  4.95
• Black-Box Inference of LLM Architectural Properties with Restrictive API Access (2026)
  Christopher Ellis et al.
  4.39
• Calibration-Family Overfit: Why Trusted Sabotage Monitors Don't Transfer Across Lineages (2026)
  Lucas Pinto
  4.39
• Is Randomness Necessary for Adaptive Data Analysis? (2026)
  Edith Cohen et al.
  4.39
• Multi-Class vs. Multi-Label BERT for CVE-to-CWE Mapping: How Taxonomy Structure Shapes the Errors (2026)
  Ana Schwengber Kelm et al.
  4.39
• Publicly-Verifiable Certificates for Statistical Algorithms (2026)
  Michael Ngo et al.
  4.39
• Guardrails as Scapegoats: Auditing Unfaithful Safety Refusals in Tool-Augmented LLM Agents (2026)
  Aarushi Singh
  4.39
• Low-rank Distributional Matrix Completion (2026)
  Jiayi Wang et al.
  4.33
• Exact Unlearning in Reinforcement Learning (2026)
  Thanh Nguyen-Tang et al.
  4.33
• Dual Advantage Fields (2026)
  Alexey Zemtsov et al.
  4.33
• CyberGym-E2E: Scalable Real-World Benchmark for AI Agents' End-to-End Cybersecurity Capabilities (2026)
  Tianneng Shi et al.
  4.33
• Unified Geometry-Guided ML-FTLE for Tracking Transient Chaos from Scalar Time Series (2026)
  S. V. Manivelan et al.
  4.33
• Generative Modeling of Discrete Latent Structures via Dynamic Policy Gradients (2026)
  Stefan Ivanovic et al.
  4.33
• Graph Neural Network leveraging Higher-order Class Label Connectivity for Heterophilous Graphs (2026)
  Takuto Takahashi et al.
  4.33
• MinhwaNet: Faithful but Insufficient Object Grounding in Korean Folk Painting (2026)
  Joonhyung Bae
  4.33
• Uncertainty-aware Multi-fidelity Closure via Conditional Normalizing Flows (2026)
  Jice Zeng et al.
  4.33
• Mitigating Manifold Departure: Uncertainty-Aware Subspace Rectification for Trustworthy MLLM Decoding (2026)
  Yingxuan Zhuang et al.
  4.33
• QSplitFL: Capability Aware Deep Q-Learning for Optimal Split Point Selection in Split Federated Learning (2026)
  Nazmus Shakib Shadin et al.
  4.33
• Rotate2Think: Geometric Priming via Orthogonal Rotation to Improve Language Model Reasoning (2026)
  Aditya Sharma et al.
  4.33
• Calibrating Overconfidence Without Sacrificing Confidence: Probe-Conditioned Head Intervention for LLMs (2026)
  Ke Li et al.
  4.33
• TD-Grokking: Learning from Zero-Reward Problems by Training-Time Decomposition (2026)
  Ningyuan Xi et al.
  4.33
• SHAPE: Coalition-Aware Expert Pruning for Sparse Mixture-of-Experts LLMs (2026)
  Yuhao Zhang
  4.33
• PreAct-Bench: Benchmarking Predictive Monitoring in LLMs (2026)
  Hainiu Xu et al.
  4.33
• LMT: A Bayesian Framework for Causal Discovery from Textual Alarm Records in Manufacturing Systems (2026)
  Xiaofeng Xiao et al.
  4.33
• A Navigable Manifold of Hypothesized Consciousness-Spectrum States in Language Model Representations (2026)
  Sophie Zhao
  4.33
• When Attribution Patching Lies: Diagnosis and a Second-Order Correction (2026)
  Luyang Zhang et al.
  4.33
• IntentKV: Cross-Turn Intent-Aware KV Cache Pruning for Agent Inference (2026)
  Junjie Li et al.
  4.33
• Co-GLANCE: Uncertainty-Aware Active Perception for Heterogeneous Robot Teaming (2026)
  Michal P. Podolinsky et al.
  4.33
• Conformal Prediction for Neural Operators: Distribution-Free Uncertainty Quantification in Physics Simulation (2026)
  Michael Chin
  4.33
• Sigma-Branch: Hierarchical Single-Path Network Reconstruction for Dynamic Inference with Reduced Active Parameters (2026)
  Kohga Tanaka et al.
  4.33
• Between Amnesia and Chaos: A Memory Stability Expressivity Trilemma for Trainable Dissipative Oscillator Networks (2026)
  Caleb Munigety
  4.33
• One Lens, Many Worlds : A Capability-Typed Interface for World-Model Interpretability (2026)
  Bhavith Chandra Challagundla et al.
  4.33
• RKSC: Reasoning-Aware KV Cache Sharing and Confident Early Exit for Multi-Step LLM Inference (2026)
  Anirudh Sekar
  4.33
• Interactions Between Crosscoder Features: A Compact Proofs Perspective (2026)
  Dmitry Manning-Coe et al.
  4.33
• Does Normalization Choice Matter for Causal Large Time-Series Models? (2026)
  Samy-Melwan Vilhes (LMAC) et al.
  4.33
• Data-aware Static Analysis: Improving Detection of Semantic Faults in Machine Learning Code Using Data Characteristics (2026)
  Willem Meijer et al.
  4.33
• HydraCIL: Decoupled Class-Incremental Learning through Prototype-Guided Multi-Head Classifiers (2026)
  Daniel Vila-Cruz et al.
  4.33
• 3SPO: State-Score-Supervised Policy Optimization for LLM Agents (2026)
  Yu Han et al.
  4.33
• Spatiotemporal Graph Transformer for 3D Neighborhood Interaction and Quality Prediction in Metal Additive Manufacturing (2026)
  Joyce Karen Pelaez et al.
  4.33
• SHAPO: Sharpness-Aware Policy Optimization for Safe Exploration (2026)
  Kaustubh Mani et al.
  4.33
• Rank Collapse, Fixed Points, and the Renormalization Group Structure of MLP Residual Networks (2026)
  Parviz Haggi-Mani et al.
  4.33
• Pre-AF 13: An Interpretable Atrial Fibrillation Risk Score Mined from Discharge Reports (2026)
  Olga Shakhmatova et al.
  4.33
• Geometrically Averaged Hard Target Updates for Linear Q-Learning (2026)
  Donghwan Lee
  4.33
• The Power of Test-Time Training for Approximate Sampling (2026)
  Noah Golowich et al.
  4.33
• Bootstrapped Monitoring: Leveraging Transparent Reasoning to Oversee Stronger AI Agents (2026)
  Frank Xiao et al.
  4.33
• DRIVE: Distributional and Retrieval-Augmented Bidding with Value Evaluation (2026)
  Miduo Cui et al.
  4.33
• A Temporal Planning Framework for Disruption Aware Dynamic Route Optimization in Heterogeneous Railway Systems (2026)
  Pollob Chandra Ray et al.
  4.33
• Giskard : Byzantine Robust and Confidential Aggregation for Large-Scale Decentralized Learning (2026)
  Ousmane Touat et al.
  4.33