{"total":19,"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":"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":"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":"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":"2510.23458","title":"BrowseConf: Confidence-Guided Test-Time Scaling for Web Agents","created":"2025-10-27","cited_by_count":5,"area":"lr"},{"id":"2508.10967","title":"Retro-Expert: Collaborative Reasoning for Interpretable Retrosynthesis","created":"2025-08-14","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":"2604.23333","title":"Process Supervision of Confidence Margin for Calibrated LLM Reasoning","created":"2026-04-25","cited_by_count":2,"area":"lr"},{"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":"2606.24281","title":"CALIBER: Calibrating Confidence Before and After Reasoning in Language Models","created":"2026-06-23","cited_by_count":1,"area":"lr"},{"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":"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":"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":"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":"2609.32470","title":"On the Pitfalls of Verbalized Confidence Priors for Calibrating Large Reasoning Models","created":"2026-09-26","cited_by_count":0,"area":"lr"},{"id":"2609.34857","title":"Beyond Verbalized Confidence: Calibrating Reasoners with Differentiable Readouts","created":"2026-09-28","cited_by_count":0,"area":"lr"},{"id":"2610.02695","title":"Test-time Calibration Learning for Large Language Model Reasoning","created":"2026-10-02","cited_by_count":0,"area":"lr"}],"next_cursor":null}