{"total":117,"rows":[{"id":"2509.04664","title":"Why Language Models Hallucinate","created":"2025-09-04","cited_by_count":220,"area":null},{"id":"2508.09138","title":"Time Is a Feature: Exploiting Temporal Dynamics in Diffusion Language Models","created":"2025-08-12","cited_by_count":33,"area":"diffusion"},{"id":"2509.25760","title":"TruthRL: Incentivizing Truthful LLMs via Reinforcement Learning","created":"2025-09-30","cited_by_count":27,"area":null},{"id":"2510.04721","title":"BrokenMath: A Benchmark for Sycophancy in Theorem Proving with LLMs","created":"2025-10-06","cited_by_count":27,"area":null},{"id":"2512.25070","title":"Scaling Open-Ended Reasoning to Predict the Future","created":"2025-12-31","cited_by_count":21,"area":"lr"},{"id":"2510.10409","title":"Trace Length is a Simple Uncertainty Signal in Reasoning Models","created":"2025-10-12","cited_by_count":19,"area":"lr"},{"id":"2512.19920","title":"Mitigating LLM Hallucination via Behaviorally Calibrated Reinforcement Learning","created":"2025-12-22","cited_by_count":18,"area":null},{"id":"2601.07264","title":"The Confidence Dichotomy: Analyzing and Mitigating Miscalibration in Tool-Use Agents","created":"2026-01-12","cited_by_count":16,"area":"agents"},{"id":"2603.09117","title":"Decoupling Reasoning and Confidence: Resurrecting Calibration in Reinforcement Learning from Verifiable Rewards","created":"2026-03-10","cited_by_count":14,"area":"lr"},{"id":"2509.14480","title":"Process-Supervised Reinforcement Learning for Interactive Multimodal Tool-Use Agents","created":"2025-09-17","cited_by_count":12,"area":"agents"},{"id":"2512.22245","title":"Calibrating LLM Judges: Linear Probes for Fast and Reliable Uncertainty Estimation","created":"2025-12-23","cited_by_count":9,"area":"mechinterp"},{"id":"2602.06948","title":"Agentic Uncertainty Reveals Agentic Overconfidence","created":"2026-02-06","cited_by_count":9,"area":"agents"},{"id":"2603.15500","title":"Understanding Reasoning in LLMs through Strategic Information Allocation under Uncertainty","created":"2026-03-16","cited_by_count":9,"area":"lr"},{"id":"2604.16830","title":"The Illusion of Certainty: Decoupling Capability and Calibration in On-Policy Distillation","created":"2026-04-18","cited_by_count":9,"area":"distill"},{"id":"2509.23129","title":"C$^2$GSPG: Confidence-calibrated Group Sequence Policy Gradient towards Self-aware Reasoning","created":"2025-09-27","cited_by_count":8,"area":"lr"},{"id":"2601.07767","title":"Are LLM Decisions Faithful to Verbal Confidence?","created":"2026-01-12","cited_by_count":8,"area":null},{"id":"2604.09529","title":"VL-Calibration: Decoupled Confidence Calibration for Large Vision-Language Models Reasoning","created":"2026-04-10","cited_by_count":8,"area":"lr"},{"id":"2609.29429","title":"Just Ask Jev: Reinforcement Learning for Calibrated Decisions as a Zero-Shot Detector of AI Alignment Failures","created":"2026-09-24","cited_by_count":8,"area":"safety"},{"id":"2601.15160","title":"Knowledge Graphs are Implicit Reward Models: Path-Derived Signals Enable Compositional Reasoning","created":"2026-01-21","cited_by_count":7,"area":"lr"},{"id":"2602.13540","title":"On Calibration of Large Language Models: From Response To Capability","created":"2026-02-14","cited_by_count":7,"area":null},{"id":"2605.15188","title":"FutureSim: Replaying World Events to Evaluate Adaptive Agents","created":"2026-05-14","cited_by_count":7,"area":null},{"id":"2512.01457","title":"Zero-Overhead Introspection for Adaptive Test-Time Compute","created":"2025-12-01","cited_by_count":6,"area":"lr"},{"id":"2601.11004","title":"NOVA: NOise-aware Verbal Confidence CAlibration for Robust Large Language Models in RAG Systems","created":"2026-01-16","cited_by_count":6,"area":"rag"},{"id":"2603.24844","title":"Reaching Beyond the Mode: RL for Distributional Reasoning in Language Models","created":"2026-03-25","cited_by_count":6,"area":"lr"},{"id":"2509.24988","title":"Generalized Correctness Models: Learning Calibrated and Model-Agnostic Correctness Predictors from Historical Patterns","created":"2025-09-29","cited_by_count":5,"area":null},{"id":"2511.11500","title":"Honesty over Accuracy: Trustworthy Language Models through Reinforced Hesitation","created":"2025-11-14","cited_by_count":5,"area":null},{"id":"2604.12632","title":"Calibration-Aware Policy Optimization for Reasoning LLMs","created":"2026-04-14","cited_by_count":5,"area":"lr"},{"id":"2608.31075","title":"Scaling Large Reasoning Models beyond Human Supervision: A Path toward Superintelligence","created":"2026-08-31","cited_by_count":5,"area":"lr"},{"id":"2510.05431","title":"Self-Filtered Distillation with LLMs-generated Trust Indicators for Reliable Patent Classification","created":"2025-10-06","cited_by_count":4,"area":null},{"id":"2510.24505","title":"CritiCal: Can Critique Help LLM Uncertainty or Confidence Calibration?","created":"2025-10-28","cited_by_count":4,"area":null},{"id":"2512.15528","title":"EmoCaliber: Advancing Reliable Visual Emotion Comprehension via Confidence Verbalization and Calibration","created":"2025-12-17","cited_by_count":4,"area":null},{"id":"2602.03507","title":"FaithRL: Learning to Reason Faithfully through Step-Level Faithfulness Maximization","created":"2026-02-03","cited_by_count":4,"area":"lr"},{"id":"2602.10231","title":"Blockwise Advantage Estimation for Multi-Objective RL with Verifiable Rewards","created":"2026-02-10","cited_by_count":4,"area":"lr"},{"id":"2603.22120","title":"StreamingClaw Technical Report","created":"2026-03-23","cited_by_count":4,"area":null},{"id":"2607.11022","title":"When the Reward Suite Is Leaky: A Preregistered Causal Contrast of Natural Verifier False Positives in RLVR","created":"2026-07-13","cited_by_count":4,"area":null},{"id":"2510.00263","title":"Judging with Confidence: Calibrating Autoraters to Preference Distributions","created":"2025-09-30","cited_by_count":3,"area":"alignment"},{"id":"2511.07318","title":"When Bias Pretends to Be Truth: How Spurious Correlations Undermine Hallucination Detection in LLMs","created":"2025-11-10","cited_by_count":3,"area":null},{"id":"2511.14275","title":"Let the Model Distribute Its Doubt: Confidence Estimation through Verbalized Probability Distribution","created":"2025-11-18","cited_by_count":3,"area":null},{"id":"2601.13284","title":"Balancing Classification and Calibration Performance in Decision-Making LLMs via Calibration Aware Reinforcement Learning","created":"2026-01-19","cited_by_count":3,"area":null},{"id":"2602.01532","title":"PRISM: Festina Lente Proactivity -- Risk-Sensitive, Uncertainty-Aware Deliberation for Proactive Agents","created":"2026-02-02","cited_by_count":3,"area":null},{"id":"2603.05881","title":"Confidence Before Answering: A Paradigm Shift for Efficient LLM Uncertainty Estimation","created":"2026-03-06","cited_by_count":3,"area":null},{"id":"2604.02621","title":"Reinforcement Learning-based Semi-supervised Knowledge Distillation with LLM-as-a-Judge","created":"2026-04-03","cited_by_count":3,"area":"lr"},{"id":"2604.08701","title":"Unified Multimodal Uncertain Inference","created":"2026-04-09","cited_by_count":3,"area":null},{"id":"2604.19444","title":"Unsupervised Confidence Calibration for Reasoning LLMs from a Single Generation","created":"2026-04-21","cited_by_count":3,"area":"lr"},{"id":"2605.27668","title":"Aligning LLMs with Human Uncertainty: A Beta-Bernoulli Calibrator for LLM Forecasting","created":"2026-05-26","cited_by_count":3,"area":null},{"id":"2606.14211","title":"Closing the Reflection Gap: A Free Calibration Bonus for Agentic RL","created":"2026-06-12","cited_by_count":3,"area":"agents"},{"id":"2607.01612","title":"Scaling with Confidence: Calibrating Confidence of LLMs for Adaptive Test Time Scaling","created":"2026-07-02","cited_by_count":3,"area":"lr"},{"id":"2608.00301","title":"Abstention as an Action Can Kill Both the Reward Gradient and the KL Anchor: Collapse Law and Repair for Error-Penalized Reinforcement Learning","created":"2026-07-31","cited_by_count":3,"area":"lr"},{"id":"2609.32160","title":"Typed Decision Models: An Early Evidence Audit and Evaluation Checklist","created":"2026-09-26","cited_by_count":3,"area":null},{"id":"2510.21007","title":"Can Confidence Estimates Decide When Chain-of-Thought Is Necessary for LLMs?","created":"2025-10-23","cited_by_count":2,"area":"lr"},{"id":"2601.05905","title":"Illusions of Confidence? Diagnosing LLM Truthfulness via Neighborhood Consistency","created":"2026-01-09","cited_by_count":2,"area":null},{"id":"2601.06786","title":"EpiCaR: Knowing What You Don't Know Matters for Better Reasoning in LLMs","created":"2026-01-11","cited_by_count":2,"area":"lr"},{"id":"2602.21857","title":"Distill and Align Decomposition for Enhanced Claim Verification","created":"2026-02-25","cited_by_count":2,"area":null},{"id":"2604.12046","title":"Think Through Uncertainty: Improving Long-Form Generation Factuality via Reasoning Calibration","created":"2026-04-13","cited_by_count":2,"area":"lr"},{"id":"2604.17293","title":"Beyond \"I Don't Know\": Evaluating LLM Self-Awareness in Discriminating Data and Model Uncertainty","created":"2026-04-19","cited_by_count":2,"area":null},{"id":"2604.23333","title":"Process Supervision of Confidence Margin for Calibrated LLM Reasoning","created":"2026-04-25","cited_by_count":2,"area":"lr"},{"id":"2605.06053","title":"Towards Generation-Efficient Uncertainty Estimation in Large Language Models","created":"2026-05-07","cited_by_count":2,"area":null},{"id":"2605.28070","title":"Bridging the Detection-to-Abstention Gap in Reasoning Models under Insufficient Information","created":"2026-05-27","cited_by_count":2,"area":"lr"},{"id":"2606.05122","title":"Self-Evaluation Is Already There: Eliciting Latent Judge Calibration in Base LLMs with Minimal Data","created":"2026-06-03","cited_by_count":2,"area":null},{"id":"2607.00164","title":"Verifiable Rewards for Calibrated Probabilistic Forecasting","created":"2026-06-30","cited_by_count":2,"area":null},{"id":"2607.03528","title":"Aligning Language Models with Selective Prediction","created":"2026-07-03","cited_by_count":2,"area":"alignment"},{"id":"2607.04332","title":"On the effectiveness of reward functions in reinforcement learning for confidence calibration of large language models","created":"2026-07-05","cited_by_count":2,"area":null},{"id":"2607.08046","title":"What LLM Forecasters Know but Don't Say: Probing Internal Representations for Calibration and Faithfulness","created":"2026-07-09","cited_by_count":2,"area":"lr"},{"id":"2607.10474","title":"Reinforcement Learning with Verifiable Physics: Post-training LLMs with Continuous Rewards","created":"2026-07-11","cited_by_count":2,"area":null},{"id":"2510.20187","title":"Every Question Has Its Own Value: Reinforcement Learning with Explicit Human Values","created":"2025-10-23","cited_by_count":1,"area":"alignment"},{"id":"2512.06533","title":"Beyond Token-level Supervision: Unlocking the Potential of Decoding-based Regression via Reinforcement Learning","created":"2025-12-06","cited_by_count":1,"area":"deeprl"},{"id":"2601.04277","title":"Unlocking the Pre-Trained Model as a Dual-Alignment Calibrator for Post-Trained LLMs","created":"2026-01-07","cited_by_count":1,"area":null},{"id":"2601.13545","title":"TruthTensor: Evaluating LLMs through Human Imitation on Prediction Market under Drift and Holistic Reasoning","created":"2026-01-20","cited_by_count":1,"area":"lr"},{"id":"2601.19862","title":"Calibration without Ground Truth","created":"2026-01-27","cited_by_count":1,"area":null},{"id":"2601.22648","title":"UCPO: Uncertainty-Aware Policy Optimization","created":"2026-01-30","cited_by_count":1,"area":null},{"id":"2602.12586","title":"Can I Have Your Order? Monte-Carlo Tree Search for Slot Filling Ordering in Diffusion Language Models","created":"2026-02-13","cited_by_count":1,"area":"diffusion"},{"id":"2603.06317","title":"From Entropy to Calibrated Uncertainty: Training Language Models to Reason About Uncertainty","created":"2026-03-06","cited_by_count":1,"area":"lr"},{"id":"2604.04220","title":"TimeSeek: Temporal Reliability of Agentic Forecasters","created":"2026-04-05","cited_by_count":1,"area":"agents"},{"id":"2604.09624","title":"Self-Calibrating Language Models via Test-Time Discriminative Distillation","created":"2026-03-18","cited_by_count":1,"area":null},{"id":"2605.15588","title":"Calibrating LLMs with Semantic-level Reward","created":"2026-05-15","cited_by_count":1,"area":null},{"id":"2605.16999","title":"Ranking-Aware Calibration for Reliable Multimodal Reinforcement Learning","created":"2026-05-16","cited_by_count":1,"area":"lr"},{"id":"2605.20740","title":"Reinforcement Learning over Predictive Distributions for LLM Regression","created":"2026-05-20","cited_by_count":1,"area":null},{"id":"2606.00251","title":"Capability Self-Assessment in Large Language Models","created":"2026-05-29","cited_by_count":1,"area":null},{"id":"2606.00869","title":"Enhancing LLM Metacognition via Cognitive Pairwise Training","created":"2026-05-30","cited_by_count":1,"area":"lr"},{"id":"2606.03731","title":"Conformal Language Modeling via Posterior Sampling","created":"2026-06-02","cited_by_count":1,"area":null},{"id":"2606.24281","title":"CALIBER: Calibrating Confidence Before and After Reasoning in Language Models","created":"2026-06-23","cited_by_count":1,"area":"lr"},{"id":"2606.32012","title":"CoMet: Context and Multiplicity Decomposition for Multimodal Uncertainty Estimation","created":"2026-06-30","cited_by_count":1,"area":null},{"id":"2608.16002","title":"From Sequence to Structure: Relational Uncertainty Propagation for LLM Agents","created":"2026-08-17","cited_by_count":1,"area":"agents"},{"id":"2608.23058","title":"LLM-based Agents for Forecasting and Prediction: Methods, Training, Evaluation, and Applications","created":"2026-08-24","cited_by_count":1,"area":"agents"},{"id":"2510.09062","title":"ReFIne: A Framework for Trustworthy Large Reasoning Models with Reliability, Faithfulness, and Interpretability","created":"2025-10-10","cited_by_count":0,"area":"lr"},{"id":"2510.10201","title":"RLFR: Extending Reinforcement Learning for LLMs with Flow Environment","created":"2025-10-11","cited_by_count":0,"area":"lr"},{"id":"2601.04731","title":"Miner:Mining Intrinsic Mastery for Data-Efficient RL in Large Reasoning Models","created":"2026-01-08","cited_by_count":0,"area":"lr"},{"id":"2602.02708","title":"BinaryPPO: Efficient Policy Optimization for Binary Classification","created":"2026-02-02","cited_by_count":0,"area":null},{"id":"2604.22110","title":"Do Not Imitate, Reinforce: Iterative Classification via Belief Refinement","created":"2026-04-23","cited_by_count":0,"area":null},{"id":"2605.06785","title":"Distributional Process Reward Models: Calibrated Prediction of Future Rewards via Conditional Optimal Transport","created":"2026-05-07","cited_by_count":0,"area":"lr"},{"id":"2605.25381","title":"Not only where, But when: Temporal Scheduling for RLVR","created":"2026-05-25","cited_by_count":0,"area":null},{"id":"2605.29532","title":"GUITestScape: Towards Open-set Evaluation on Exploratory GUI Testing","created":"2026-05-28","cited_by_count":0,"area":"agents"},{"id":"2605.31464","title":"GPU Forecasters: Language Models as Selective Surrogates for Kernel Runtime Optimization","created":"2026-05-29","cited_by_count":0,"area":"agents"},{"id":"2606.20585","title":"Turning Intent into Specifications: A Benchmark and an Interactive User-Assistant Agent","created":"2026-05-13","cited_by_count":0,"area":null},{"id":"2606.24937","title":"The Hitchhiker's Guide to Agentic AI: From Foundations to Systems","created":"2026-06-22","cited_by_count":0,"area":"lr"},{"id":"2608.20771","title":"CAS: Conformalized Agentic Search via Adaptive Retrieval and Policy Weighting","created":"2026-08-21","cited_by_count":0,"area":"agents"},{"id":"2609.00935","title":"DualStake: Dual-Path Confidence Calibration in Deep Research Agents","created":"2026-09-01","cited_by_count":0,"area":"agents"},{"id":"2609.18453","title":"The Mirage of Calibrated Confidence: Trajectory-Independence of Verbalized Confidence in Vision-Language Models","created":"2026-09-16","cited_by_count":0,"area":"mllm"},{"id":"2609.31619","title":"Learning to Stop without Learning to Stop: Self-Supervised Confidence Training Improves Reasoning Efficiency","created":"2026-09-25","cited_by_count":0,"area":"lr"},{"id":"2609.32470","title":"On the Pitfalls of Verbalized Confidence Priors for Calibrating Large Reasoning Models","created":"2026-09-26","cited_by_count":0,"area":"lr"}],"next_cursor":"100"}