{"total":35,"rows":[{"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":"2505.22660","title":"Maximizing Confidence Alone Improves Reasoning","created":"2025-05-28","cited_by_count":100,"area":"lr"},{"id":"2609.26550","title":"JEV-as-a-Judge: Accept When Confident, Escalate When Unsure","created":"2026-09-22","cited_by_count":30,"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":"2506.04909","title":"When Thinking LLMs Lie: Unveiling the Strategic Deception in Representations of Reasoning Models","created":"2025-06-05","cited_by_count":18,"area":"lr"},{"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":"2505.19184","title":"When Two LLMs Debate, Both Think They'll Win","created":"2025-05-25","cited_by_count":10,"area":"lr"},{"id":"2506.19467","title":"Can Reasoning Help Large Language Models Capture Human Annotator Disagreement?","created":"2025-06-24","cited_by_count":10,"area":"lr"},{"id":"2506.03723","title":"Verbalized Confidence Triggers Self-Verification: Emergent Behavior Without Explicit Reasoning Supervision","created":"2025-06-04","cited_by_count":9,"area":"lr"},{"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":"2601.23163","title":"Probing the Trajectories of Reasoning Traces in Large Language Models","created":"2026-01-30","cited_by_count":7,"area":"lr"},{"id":"2601.03154","title":"Decoupling the Effect of Chain-of-Thought Reasoning: A Human Label Variation Perspective","created":"2026-01-06","cited_by_count":6,"area":"lr"},{"id":"2603.16728","title":"The Cost of Reasoning: Chain-of-Thought Induces Overconfidence in Vision-Language Models","created":"2026-03-17","cited_by_count":5,"area":"lr"},{"id":"2606.18089","title":"From Reasoning Traces to Reusable Modules: Understanding Compositional Generalization in Language Model Reasoning","created":"2026-06-16","cited_by_count":5,"area":"lr"},{"id":"2510.19176","title":"The Zero-Step Thinking: An Empirical Study of Mode Selection as Harder Early Exit in Reasoning Models","created":"2025-10-22","cited_by_count":4,"area":"lr"},{"id":"2511.02130","title":"Re-FORC: Adaptive Reward Prediction for Efficient Chain-of-Thought Reasoning","created":"2025-11-03","cited_by_count":4,"area":"lr"},{"id":"2601.08134","title":"How Reliable are Confidence Estimators for Large Reasoning Models? A Systematic Benchmark on High-Stakes Domains","created":"2026-01-13","cited_by_count":4,"area":"lr"},{"id":"2510.21049","title":"Reasoning's Razor: Reasoning Improves Accuracy but Can Hurt Recall at Critical Operating Points in Safety and Hallucination Detection","created":"2025-10-23","cited_by_count":3,"area":"lr"},{"id":"2604.06389","title":"SELFDOUBT: Uncertainty Quantification for Reasoning LLMs via the Hedge-to-Verify Ratio","created":"2026-04-07","cited_by_count":3,"area":"lr"},{"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":"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":"2509.24884","title":"Expanding Computation Spaces of LLMs at Inference Time","created":"2025-09-29","cited_by_count":2,"area":"lr"},{"id":"2512.01725","title":"Beware of Reasoning Overconfidence: Pitfalls in the Reasoning Process for Multi-solution Tasks","created":"2025-12-01","cited_by_count":2,"area":"lr"},{"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":"2604.22266","title":"Large Language Models Decide Early and Explain Later","created":"2026-04-24","cited_by_count":2,"area":"lr"},{"id":"2606.03969","title":"Quantifying Faithful Confidence Expression in Large Reasoning Models","created":"2026-06-02","cited_by_count":2,"area":"lr"},{"id":"2512.00729","title":"Probing the \"Psyche'' of Large Reasoning Models: Understanding Through a Human Lens","created":"2025-11-30","cited_by_count":1,"area":"lr"},{"id":"2601.17421","title":"Oops, Wait: Discourse Tokens Matter in Reasoning Model","created":"2026-01-24","cited_by_count":1,"area":"lr"},{"id":"2603.19118","title":"How Uncertainty Estimation Scales with Sampling in Reasoning Models","created":"2026-03-19","cited_by_count":1,"area":"lr"},{"id":"2510.21067","title":"The Virtues of Brevity: Avoid Overthinking in Parallel Test-Time Reasoning","created":"2025-10-24","cited_by_count":0,"area":"lr"},{"id":"2511.15921","title":"Thinking, Faithful and Stable: Mitigating Hallucinations in LLMs","created":"2025-11-19","cited_by_count":0,"area":"lr"},{"id":"2606.13649","title":"Operadic consistency: a label-free signal for compositional reasoning failures in LLMs","created":"2026-06-11","cited_by_count":0,"area":"lr"},{"id":"2607.26845","title":"Thinking Under Uncertainty: Evidence Use and Information-Seeking in Language Models","created":"2026-07-29","cited_by_count":0,"area":"lr"},{"id":"2608.09898","title":"Consilience for Verifier-Free Test-Time Scaling","created":"2026-08-10","cited_by_count":0,"area":"lr"},{"id":"2609.33290","title":"Calibration, Not Answer Selection: Distilling Internal Confidence in Reasoning Models","created":"2026-09-27","cited_by_count":0,"area":"lr"}],"next_cursor":null}