{"total":29,"rows":[{"id":"2509.08827","title":"A Survey of Reinforcement Learning for Large Reasoning Models","created":"2025-09-10","cited_by_count":180,"area":"lr"},{"id":"2508.02120","title":"Don't Overthink It: A Survey of Efficient R1-style Large Reasoning Models","created":"2025-08-04","cited_by_count":37,"area":"lr"},{"id":"2509.06948","title":"Beyond Two-Stage Training: Cooperative SFT and RL for LLM Reasoning","created":"2025-09-08","cited_by_count":30,"area":"lr"},{"id":"2509.03871","title":"A Comprehensive Survey on Trustworthiness in Reasoning with Large Language Models","created":"2025-09-04","cited_by_count":25,"area":"lr"},{"id":"2602.13517","title":"Think Deep, Not Just Long: Measuring LLM Reasoning Effort via Deep-Thinking Tokens","created":"2026-02-13","cited_by_count":22,"area":"lr"},{"id":"2506.19807","title":"KnowRL: Exploring Knowledgeable Reinforcement Learning for Factuality","created":"2025-06-24","cited_by_count":20,"area":"lr"},{"id":"2601.20614","title":"Harder Is Better: Boosting Mathematical Reasoning via Difficulty-Aware GRPO and Multi-Aspect Question Reformulation","created":"2026-01-28","cited_by_count":19,"area":"lr"},{"id":"2507.09662","title":"Towards Concise and Adaptive Thinking in Large Reasoning Models: A Survey","created":"2025-07-13","cited_by_count":18,"area":"lr"},{"id":"2508.02511","title":"Test-time Prompt Intervention","created":"2025-08-04","cited_by_count":12,"area":"lr"},{"id":"2603.13366","title":"Thinking in Uncertainty: Mitigating Hallucinations in MLRMs with Latent Entropy-Aware Decoding","created":"2026-03-09","cited_by_count":12,"area":"lr"},{"id":"2508.08088","title":"HierSearch: A Hierarchical Enterprise Deep Search Framework Integrating Local and Web Searches","created":"2025-08-11","cited_by_count":7,"area":"lr"},{"id":"2602.09305","title":"Reward Modeling for Reinforcement Learning-Based LLM Reasoning: Design, Challenges, and Evaluation","created":"2026-02-10","cited_by_count":7,"area":"lr"},{"id":"2601.19928","title":"Towards a Mechanistic Understanding of Large Reasoning Models: A Survey of Training, Inference, and Failures","created":"2026-01-11","cited_by_count":6,"area":"lr"},{"id":"2601.02170","title":"Streaming Hallucination Detection in Long Chain-of-Thought Reasoning","created":"2026-01-05","cited_by_count":5,"area":"lr"},{"id":"2603.10384","title":"Beyond Scalars: Evaluating and Understanding LLM Reasoning via Geometric Progress and Stability","created":"2026-03-11","cited_by_count":5,"area":"lr"},{"id":"2506.21571","title":"Towards Understanding the Cognitive Habits of Large Reasoning Models","created":"2025-06-13","cited_by_count":4,"area":"lr"},{"id":"2510.24794","title":"MR-Align: Meta-Reasoning Informed Factuality Alignment for Large Reasoning Models","created":"2025-10-27","cited_by_count":4,"area":"lr"},{"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":"2603.12372","title":"Efficient Reasoning with Balanced Thinking","created":"2026-03-12","cited_by_count":4,"area":"lr"},{"id":"2510.00319","title":"DecepChain: Inducing Deceptive Reasoning in Large Language Models","created":"2025-09-30","cited_by_count":3,"area":"lr"},{"id":"2607.05861","title":"Mitigating Factual Hallucination in Large Reasoning Models via Mixed-Mode Advantage Regularization","created":"2026-07-07","cited_by_count":3,"area":"lr"},{"id":"2508.12265","title":"Fast, Slow, and Tool-augmented Thinking for LLMs: A Review","created":"2025-08-17","cited_by_count":2,"area":"lr"},{"id":"2602.00085","title":"CARE-RFT: Confidence-Anchored Reinforcement Finetuning for Reliable Reasoning in Large Language Models","created":"2026-01-22","cited_by_count":2,"area":"lr"},{"id":"2603.25412","title":"Beyond Content Safety: Real-Time Monitoring for Reasoning Vulnerabilities in Large Language Models","created":"2026-03-26","cited_by_count":2,"area":"lr"},{"id":"2601.17467","title":"Harnessing Reasoning Trajectories for Hallucination Detection via Answer-agreement Representation Shaping","created":"2026-01-24","cited_by_count":0,"area":"lr"},{"id":"2606.07108","title":"DyCon: Dynamic Reasoning Control via Evolving Difficulty Modeling","created":"2026-06-05","cited_by_count":0,"area":"lr"},{"id":"2607.18915","title":"Reasoning Error from Known Fact: Step-Level Self-Consistency Group Relative Policy Optimization for LLM","created":"2026-07-21","cited_by_count":0,"area":"lr"},{"id":"2610.05472","title":"Hallucination Across the Reasoning Lifecycle: Interface Visibility, Causal Evidence, and Release Control in Large Reasoning Models","created":"2026-10-04","cited_by_count":0,"area":"lr"},{"id":"2610.12601","title":"Reflective Prompt Optimization of a Deep-Research Agent: A Topic-Disjoint, Multi-Seed Protocol for Measuring Transferable Gains and Prompt-Level Overfitting","created":"2026-10-08","cited_by_count":0,"area":"lr"}],"next_cursor":null}