{"total":26,"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":"2505.14489","title":"Reasoning Models Better Express Their Confidence","created":"2025-05-20","cited_by_count":65,"area":"lr"},{"id":"2509.26209","title":"Diversity-Incentivized Exploration for Versatile Reasoning","created":"2025-09-30","cited_by_count":28,"area":"lr"},{"id":"2502.04392","title":"Division-of-Thoughts: Harnessing Hybrid Language Model Synergy for Efficient On-Device Agents","created":"2025-02-06","cited_by_count":25,"area":"lr"},{"id":"2502.17214","title":"CoT-UQ: Improving Response-wise Uncertainty Quantification in LLMs with Chain-of-Thought","created":"2025-02-24","cited_by_count":23,"area":"lr"},{"id":"2506.13351","title":"Direct Reasoning Optimization: Token-Level Reasoning Reflectivity Meets Rubric Gates for Unverifiable Tasks","created":"2025-06-16","cited_by_count":18,"area":"lr"},{"id":"2505.07961","title":"Making Small Language Models Efficient Reasoners: Intervention, Supervision, Reinforcement","created":"2025-05-12","cited_by_count":14,"area":"lr"},{"id":"2510.24051","title":"Pie: A Programmable Serving System for Emerging LLM Applications","created":"2025-10-28","cited_by_count":14,"area":"lr"},{"id":"2602.01062","title":"SetPO: Set-Level Policy Optimization for Diversity-Preserving LLM Reasoning","created":"2026-02-01","cited_by_count":11,"area":"lr"},{"id":"2510.09913","title":"Don't Throw Away Your Pretrained Model","created":"2025-10-10","cited_by_count":10,"area":"lr"},{"id":"2511.06190","title":"Confidence-Guided Stepwise Model Routing for Cost-Efficient Reasoning","created":"2025-11-09","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":"2506.17336","title":"PPMI: Privacy-Preserving LLM Interaction with Socratic Chain-of-Thought Reasoning and Homomorphically Encrypted Vector Databases","created":"2025-06-19","cited_by_count":6,"area":"lr"},{"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":"2602.05307","title":"MentorCollab: Large-to-Small Inference-Time Mentorship for Concise Reasoning in Language Models","created":"2026-02-05","cited_by_count":2,"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":"2604.02230","title":"Answering the Wrong Question: Reasoning Trace Inversion for Abstention in LLMs","created":"2026-04-02","cited_by_count":0,"area":"lr"},{"id":"2604.26173","title":"Entropy Centroids as Intrinsic Rewards for Test-Time Scaling","created":"2026-04-28","cited_by_count":0,"area":"lr"},{"id":"2606.15308","title":"Forced Deferral: Manipulating Routing Decisions in Multimodal LLM Cascades","created":"2026-06-13","cited_by_count":0,"area":"lr"},{"id":"2607.16727","title":"Constraint-Anchored Reasoning Traces","created":"2026-07-18","cited_by_count":0,"area":"lr"},{"id":"2608.15817","title":"RLCascadeRouter: Quality-Estimator-Free Cascade Routing via Reinforcement Learning","created":"2026-08-16","cited_by_count":0,"area":"lr"},{"id":"2608.22839","title":"Hierarchy-Aware Supervised Uncertainty Estimation for Black-box LLM Taxonomic Reasoning","created":"2026-08-24","cited_by_count":0,"area":"lr"},{"id":"2609.34454","title":"When Words Fall Short: Iterative Synergy Between Verbalized Reasoning and Hidden Features for LLM Confidence Estimation","created":"2026-09-28","cited_by_count":0,"area":"lr"},{"id":"2610.17309","title":"StartLux-Decision: AutoThink Decision Models with Reinforcement Learning for Calibrated Deliberative Decisions","created":"2026-10-12","cited_by_count":0,"area":"lr"},{"id":"2610.20328","title":"Argument Graph Uncertainty: Quantifying Uncertainty from the Logical Structure of Reasoning Chains","created":"2026-10-14","cited_by_count":0,"area":"lr"}],"next_cursor":null}