{"total":112,"rows":[{"id":"2504.01990","title":"Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems","created":"2025-03-31","cited_by_count":126,"area":"agents"},{"id":"2507.16806","title":"Beyond Binary Rewards: Training LMs to Reason About Their Uncertainty","created":"2025-07-22","cited_by_count":117,"area":"lr"},{"id":"2503.00031","title":"Efficient Test-Time Scaling via Self-Calibration","created":"2025-02-25","cited_by_count":75,"area":"lr"},{"id":"2503.22674","title":"QuestBench: Can LLMs ask the right question to acquire information in reasoning tasks?","created":"2025-03-28","cited_by_count":63,"area":"lr"},{"id":"2503.02623","title":"Rewarding Doubt: A Reinforcement Learning Approach to Calibrated Confidence Expression of Large Language Models","created":"2025-03-04","cited_by_count":52,"area":null},{"id":"2502.11028","title":"Mind the Confidence Gap: Overconfidence, Calibration, and Distractor Effects in Large Language Models","created":"2025-02-16","cited_by_count":40,"area":null},{"id":"2505.01997","title":"Restoring Calibration for Aligned Large Language Models: A Calibration-Aware Fine-Tuning Approach","created":"2025-05-04","cited_by_count":25,"area":"alignment"},{"id":"2506.00582","title":"Do Language Models Mirror Human Confidence? Exploring Psychological Insights to Address Overconfidence in LLMs","created":"2025-05-31","cited_by_count":19,"area":null},{"id":"2507.10587","title":"Anthropomimetic Uncertainty: What Verbalized Uncertainty in Language Models is Missing","created":"2025-07-11","cited_by_count":14,"area":null},{"id":"2509.25532","title":"Calibrating Verbalized Confidence with Self-Generated Distractors","created":"2025-09-29","cited_by_count":14,"area":"synth"},{"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":"2412.03338","title":"AI-Driven Day-to-Day Route Choice","created":"2024-12-04","cited_by_count":13,"area":null},{"id":"2412.09544","title":"Sail into the Headwind: Alignment via Robust Rewards and Dynamic Labels against Reward Hacking","created":"2024-12-12","cited_by_count":13,"area":"alignment"},{"id":"2505.17510","title":"Large Language Models Do Multi-Label Classification Differently","created":"2025-05-23","cited_by_count":13,"area":null},{"id":"2509.21882","title":"Position: The Hidden Costs and Measurement Gaps of Reinforcement Learning with Verifiable Rewards","created":"2025-09-26","cited_by_count":12,"area":null},{"id":"2602.14233","title":"Evaluating LLMs in Finance Requires Explicit Bias Consideration","created":"2026-02-15","cited_by_count":11,"area":null},{"id":"2505.19184","title":"When Two LLMs Debate, Both Think They'll Win","created":"2025-05-25","cited_by_count":10,"area":"lr"},{"id":"2510.10913","title":"ADVICE: Answer-Dependent Verbalized Confidence Estimation","created":"2025-10-13","cited_by_count":10,"area":null},{"id":"2512.24661","title":"Do Large Language Models Know What They Are Capable Of?","created":"2025-12-31","cited_by_count":10,"area":null},{"id":"2605.11436","title":"Agent-BRACE: Decoupling Beliefs from Actions in Long-Horizon Tasks via Verbalized State Uncertainty","created":"2026-05-12","cited_by_count":10,"area":"agents"},{"id":"2505.17773","title":"C-LoRA: Contextual Low-Rank Adaptation for Uncertainty Estimation in Large Language Models","created":"2025-05-23","cited_by_count":9,"area":null},{"id":"2511.00280","title":"Calibration Across Layers: Understanding Calibration Evolution in LLMs","created":"2025-10-31","cited_by_count":9,"area":null},{"id":"2603.06612","title":"Consensus is Not Verification: Why Crowd Wisdom Strategies Fail for LLM Truthfulness","created":"2026-02-20","cited_by_count":9,"area":null},{"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":"2505.22787","title":"Can Large Language Models Match the Conclusions of Systematic Reviews?","created":"2025-05-28","cited_by_count":8,"area":null},{"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":"2601.03042","title":"BaseCal: Unsupervised Confidence Calibration via Base Model Signals","created":"2026-01-06","cited_by_count":8,"area":null},{"id":"2603.06604","title":"Know When You're Wrong: Aligning Confidence with Correctness for LLM Error Detection","created":"2026-02-18","cited_by_count":8,"area":"alignment"},{"id":"2603.25052","title":"Closing the Confidence-Faithfulness Gap in Large Language Models","created":"2026-03-26","cited_by_count":8,"area":"mechinterp"},{"id":"2411.06528","title":"Epistemic Integrity in Large Language Models","created":"2024-11-10","cited_by_count":7,"area":null},{"id":"2606.30850","title":"BayesBench: Evaluating LLM Belief Trajectories Under Multi-Turn Evidence Accumulation","created":"2026-06-29","cited_by_count":7,"area":null},{"id":"2505.10597","title":"Two Minds Better Than One: Collaborative Reward Modeling for LLM Alignment","created":"2025-05-15","cited_by_count":6,"area":"alignment"},{"id":"2506.02945","title":"Quantitative LLM Judges","created":"2025-06-03","cited_by_count":6,"area":null},{"id":"2604.05306","title":"LLMs Should Express Uncertainty Explicitly","created":"2026-04-07","cited_by_count":6,"area":null},{"id":"2606.03437","title":"Large Language Models Are Overconfident in Their Own Responses","created":"2026-06-02","cited_by_count":6,"area":null},{"id":"2510.23458","title":"BrowseConf: Confidence-Guided Test-Time Scaling for Web Agents","created":"2025-10-27","cited_by_count":5,"area":"lr"},{"id":"2511.11500","title":"Honesty over Accuracy: Trustworthy Language Models through Reinforced Hesitation","created":"2025-11-14","cited_by_count":5,"area":null},{"id":"2604.03904","title":"I-CALM: Incentivizing Confidence-Aware Abstention for LLM Selective Answering","created":"2026-04-05","cited_by_count":5,"area":null},{"id":"2601.23096","title":"CATTO: Balancing Preferences and Confidence in Language Models","created":"2026-01-30","cited_by_count":4,"area":"alignment"},{"id":"2602.16162","title":"LLMs Exhibit Significantly Lower Uncertainty in Creative Writing Than Professional Writers","created":"2026-02-18","cited_by_count":4,"area":null},{"id":"2603.24124","title":"The Alignment Tax: Response Homogenization in Aligned LLMs and Its Implications for Uncertainty Estimation","created":"2026-03-25","cited_by_count":4,"area":"alignment"},{"id":"2604.01457","title":"Wired for Overconfidence: A Mechanistic Perspective on Inflated Verbalized Confidence in LLMs","created":"2026-04-01","cited_by_count":4,"area":null},{"id":"2606.06306","title":"Decomposing Factual Sycophancy in Language Models: How Size and Instruction Tuning Shape Robustness","created":"2026-06-04","cited_by_count":4,"area":null},{"id":"2606.32032","title":"Reinforcement Learning with Metacognitive Feedback Elicits Faithful Uncertainty Expression in LLMs","created":"2026-06-30","cited_by_count":4,"area":"alignment"},{"id":"2508.10967","title":"Retro-Expert: Collaborative Reasoning for Interpretable Retrosynthesis","created":"2025-08-14","cited_by_count":3,"area":"lr"},{"id":"2509.06770","title":"Another Turn, Better Output? A Turn-Wise Analysis of Iterative LLM Prompting","created":"2025-09-08","cited_by_count":3,"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":"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":"2603.03291","title":"One Bias After Another: Mechanistic Reward Shaping and Persistent Biases in Language Reward Models","created":"2026-02-06","cited_by_count":3,"area":"alignment"},{"id":"2603.05801","title":"Ambiguity Collapse by LLMs: A Taxonomy of Epistemic Risks","created":"2026-03-06","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":"2604.19444","title":"Unsupervised Confidence Calibration for Reasoning LLMs from a Single Generation","created":"2026-04-21","cited_by_count":3,"area":"lr"},{"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":"2606.22027","title":"RARM: Confidence-Gated Progress Reward Modeling for RL in Manipulation","created":"2026-06-20","cited_by_count":3,"area":"alignment"},{"id":"2606.27023","title":"Just how sure are you? Improving Verbalized Uncertainty Calibration in Medical VQA","created":"2026-06-25","cited_by_count":3,"area":"mllm"},{"id":"2411.17912","title":"Can LLMs plan paths in the real world?","created":"2024-11-26","cited_by_count":2,"area":null},{"id":"2502.06173","title":"Uncertainty-Aware Adaptation of Large Language Models for Protein-Protein Interaction Analysis","created":"2025-02-10","cited_by_count":2,"area":null},{"id":"2510.03231","title":"Reward Models are Metrics in a Trench Coat","created":"2025-10-03","cited_by_count":2,"area":"alignment"},{"id":"2510.22866","title":"Interpreting and Mitigating Unwanted Uncertainty in LLMs","created":"2025-10-26","cited_by_count":2,"area":null},{"id":"2602.06022","title":"Correctness-Optimized Residual Activation Lens (CORAL): Transferrable and Calibration-Aware Inference-Time Steering","created":"2026-02-05","cited_by_count":2,"area":null},{"id":"2602.13571","title":"LLM-Confidence Reranker: A Training-Free Approach for Enhancing Retrieval-Augmented Generation Systems","created":"2026-02-14","cited_by_count":2,"area":"rag"},{"id":"2604.23333","title":"Process Supervision of Confidence Margin for Calibrated LLM Reasoning","created":"2026-04-25","cited_by_count":2,"area":"lr"},{"id":"2605.17480","title":"The Capability Paradox: How Smarter Auditors Make Multi-Agent Systems Less Secure","created":"2026-05-17","cited_by_count":2,"area":"agents"},{"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":"2505.11731","title":"Dist2ill: Distributional Distillation for One-Pass Uncertainty Estimation in Large Language Models","created":"2025-05-16","cited_by_count":1,"area":null},{"id":"2512.06343","title":"When Distance Distracts: Representation Distance Bias in BT-Loss for Reward Models","created":"2025-12-06","cited_by_count":1,"area":"alignment"},{"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":"2601.19862","title":"Calibration without Ground Truth","created":"2026-01-27","cited_by_count":1,"area":null},{"id":"2604.20500","title":"Efficient Test-Time Inference via Deterministic Exploration of Truncated Decoding Trees","created":"2026-04-22","cited_by_count":1,"area":"lr"},{"id":"2605.23909","title":"Confidence Calibration in Large Language Models","created":"2026-04-03","cited_by_count":1,"area":null},{"id":"2606.09876","title":"Calibrating Overconfidence Without Sacrificing Confidence: Probe-Conditioned Head Intervention for LLMs","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":"2606.31371","title":"Calibrating the Evaluator: Does Probability Calibration Mitigate Preference Coupling in LLM Agent Feedback Loops?","created":"2026-06-30","cited_by_count":1,"area":"agents"},{"id":"2607.11881","title":"Metacognition in LLMs: Foundations, Progress, and Opportunities","created":"2026-07-13","cited_by_count":1,"area":null},{"id":"2608.24691","title":"Confident at the moment of action: belief miscalibration in LLM play under hidden information","created":"2026-08-25","cited_by_count":1,"area":"agents"},{"id":"2503.00563","title":"A Guide to Failure in Machine Learning: Reliability and Robustness from Foundations to Practice","created":"2025-03-01","cited_by_count":0,"area":null},{"id":"2504.15434","title":"AGI Is Coming... Right After AI Learns to Play Wordle","created":"2025-04-21","cited_by_count":0,"area":null},{"id":"2508.17182","title":"LLM Assertiveness can be Mechanistically Decomposed into Emotional and Logical Components","created":"2025-08-24","cited_by_count":0,"area":"mechinterp"},{"id":"2603.09985","title":"The Dunning-Kruger Effect in Large Language Models: An Empirical Study of Confidence Calibration","created":"2026-02-12","cited_by_count":0,"area":null},{"id":"2603.19744","title":"Rethinking Ground Truth: A Case Study on Human Label Variation in MLLM Benchmarking","created":"2026-03-20","cited_by_count":0,"area":"lr"},{"id":"2603.29492","title":"Calibrated Confidence Expression for Radiology Report Generation","created":"2026-03-31","cited_by_count":0,"area":"mllm"},{"id":"2604.08454","title":"Less Data Approximates More: Earning Faithful Confidence in High-Stakes Domains","created":"2026-04-09","cited_by_count":0,"area":null},{"id":"2604.08974","title":"Confident in a Confidence Score: Investigating the Sensitivity of Confidence Scores to Supervised Fine-Tuning","created":"2026-04-10","cited_by_count":0,"area":null},{"id":"2604.14651","title":"CURA: Clinical Uncertainty Risk Alignment for Language Model-Based Risk Prediction","created":"2026-04-16","cited_by_count":0,"area":"alignment"},{"id":"2604.15602","title":"GroupDPO: Memory-Efficient Group-Wise Direct Preference Optimization","created":"2026-04-17","cited_by_count":0,"area":"alignment"},{"id":"2604.16615","title":"Beyond Feature Fusion: Contextual Bayesian PEFT for Multimodal Uncertainty Estimation","created":"2026-04-17","cited_by_count":0,"area":null},{"id":"2604.16657","title":"Cross-Modal Bayesian Low-Rank Adaptation for Uncertainty-Aware Multimodal Learning","created":"2026-04-17","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":"2605.29888","title":"LaRA: Layer-wise Representation Analysis for Detecting Data Contamination in RL Post-Training","created":"2026-05-28","cited_by_count":0,"area":"lr"},{"id":"2605.30487","title":"Configurable Reward Model for Balanced Safety Alignment","created":"2026-05-28","cited_by_count":0,"area":"alignment"},{"id":"2607.20529","title":"Uncertainty-Aware Trust Estimation for Multi-LLM Systems via Structured Expert Judgement","created":"2026-07-10","cited_by_count":0,"area":null},{"id":"2607.26981","title":"OptimismBench: Forecasting Bias and the Alignment Effect in Language Model Judgment","created":"2026-07-29","cited_by_count":0,"area":null},{"id":"2608.07419","title":"Beyond Post-Hoc Temperature Scaling: Bilevel Optimization for LLM Calibration","created":"2026-08-07","cited_by_count":0,"area":null},{"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":"2608.25428","title":"DCGC: Draft-Conditioned Global Correction for Complex Reasoning with Masked Diffusion Models","created":"2026-08-26","cited_by_count":0,"area":"lr"},{"id":"2608.31022","title":"MNIST-PRO: MNIST is Back as a Partially Observable World for AI Agents","created":"2026-08-31","cited_by_count":0,"area":null},{"id":"2609.07395","title":"Uncertainty Quantification for LLM Agents: A Taxonomy, an Evaluation Protocol, and an Empirical Study","created":"2026-09-07","cited_by_count":0,"area":"agents"},{"id":"2609.09707","title":"Which Tokens Should SFT Actually Learn? A Token-Trimming Perspective on Mathematical Reasoning","created":"2026-09-09","cited_by_count":0,"area":"lr"},{"id":"2609.18320","title":"Attention Dispersion as a Diagnostic Signal for Hallucination in Large Language Models","created":"2026-09-16","cited_by_count":0,"area":null}],"next_cursor":"100"}