{"total":31,"rows":[{"id":"2505.07686","title":"S-GRPO: Early Exit via Reinforcement Learning in Reasoning Models","created":"2025-05-12","cited_by_count":87,"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":"2505.16838","title":"R1-Compress: Long Chain-of-Thought Compression via Chunk Compression and Search","created":"2025-05-22","cited_by_count":30,"area":"lr"},{"id":"2602.08354","title":"Does Your Reasoning Model Implicitly Know When to Stop Thinking?","created":"2026-02-09","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":"2510.10103","title":"Stop When Enough: Adaptive Early-Stopping for Chain-of-Thought Reasoning","created":"2025-10-11","cited_by_count":16,"area":"lr"},{"id":"2508.11582","title":"Aware First, Think Less: Dynamic Boundary Self-Awareness Drives Extreme Reasoning Efficiency in Large Language Models","created":"2025-08-15","cited_by_count":13,"area":"lr"},{"id":"2601.21919","title":"Self-Compression of Chain-of-Thought via Multi-Agent Reinforcement Learning","created":"2026-01-29","cited_by_count":13,"area":"lr"},{"id":"2507.15758","title":"LAPO: Internalizing Reasoning Efficiency via Length-Adaptive Policy Optimization","created":"2025-07-21","cited_by_count":11,"area":"lr"},{"id":"2507.15844","title":"Hierarchical Budget Policy Optimization for Adaptive Reasoning","created":"2025-07-21","cited_by_count":8,"area":"lr"},{"id":"2511.10714","title":"BadThink: Triggered Overthinking Attacks on Chain-of-Thought Reasoning in Large Language Models","created":"2025-11-13","cited_by_count":8,"area":"lr"},{"id":"2601.11340","title":"Neural Chain-of-Thought Search: Searching the Optimal Reasoning Path to Enhance Large Language Models","created":"2026-01-16","cited_by_count":8,"area":"lr"},{"id":"2601.22069","title":"VTC-R1: Vision-Text Compression for Efficient Long-Context Reasoning","created":"2026-01-29","cited_by_count":8,"area":"lr"},{"id":"2603.14251","title":"Mitigating Overthinking in Large Reasoning Language Models via Reasoning Path Deviation Monitoring","created":"2026-03-15","cited_by_count":6,"area":"lr"},{"id":"2604.06787","title":"When Is Thinking Enough? Early Exit via Sufficiency Assessment for Efficient Reasoning","created":"2026-04-08","cited_by_count":6,"area":"lr"},{"id":"2510.08026","title":"PEAR: Phase Entropy Aware Reward for Efficient Reasoning","created":"2025-10-09","cited_by_count":5,"area":"lr"},{"id":"2508.04460","title":"From \"Aha Moments\" to Controllable Thinking: Toward Meta-Cognitive Reasoning in Large Reasoning Models via Decoupled Reasoning and Control","created":"2025-08-06","cited_by_count":4,"area":"lr"},{"id":"2602.05539","title":"Steering Large Reasoning Models towards Concise Reasoning via Flow Matching","created":"2026-02-05","cited_by_count":4,"area":"lr"},{"id":"2602.22642","title":"Compress the Easy, Explore the Hard: Difficulty-Aware Entropy Regularization for Efficient LLM Reasoning","created":"2026-02-26","cited_by_count":4,"area":"lr"},{"id":"2510.03259","title":"Verifying Meta-Awareness via Predictive Rewards in Reasoning Models","created":"2025-09-26","cited_by_count":3,"area":"lr"},{"id":"2510.23486","title":"Learning to Reason Efficiently with Discounted Reinforcement Learning","created":"2025-10-27","cited_by_count":3,"area":"lr"},{"id":"2512.17901","title":"When Reasoning Meets Its Laws","created":"2025-12-19","cited_by_count":3,"area":"lr"},{"id":"2602.08948","title":"CoRefine: Confidence-Guided Self-Refinement for Adaptive Test-Time Compute","created":"2026-02-09","cited_by_count":3,"area":"lr"},{"id":"2602.12113","title":"Stop Unnecessary Reflection: Training LRMs for Efficient Reasoning with Adaptive Reflection and Length Coordinated Penalty","created":"2026-02-12","cited_by_count":2,"area":"lr"},{"id":"2602.14917","title":"BFS-PO: Best-First Search for Large Reasoning Models","created":"2026-02-16","cited_by_count":2,"area":"lr"},{"id":"2606.03503","title":"ThoughtFold: Folding Reasoning Chains via Introspective Preference Learning","created":"2026-06-02","cited_by_count":1,"area":"lr"},{"id":"2607.28707","title":"Demystifying Entropy-based Selection for Chain-of-Thought Compression in Large Reasoning Models","created":"2026-07-30","cited_by_count":1,"area":"lr"},{"id":"2601.22484","title":"Mitigating Cognitive Inertia in Large Reasoning Models via Latent Spike Steering","created":"2026-01-30","cited_by_count":0,"area":"lr"},{"id":"2602.14451","title":"Precedent-Informed Reasoning: Mitigating Overthinking in Large Reasoning Models via Test-Time Precedent Learning","created":"2026-02-16","cited_by_count":0,"area":"lr"},{"id":"2605.23074","title":"PathCal: State-Aware Reflection-Marker Calibration for Efficient Reasoning","created":"2026-05-21","cited_by_count":0,"area":"lr"},{"id":"2609.31619","title":"Learning to Stop without Learning to Stop: Self-Supervised Confidence Training Improves Reasoning Efficiency","created":"2026-09-25","cited_by_count":0,"area":"lr"}],"next_cursor":null}