{"list":"closest","total":95,"rows":[{"id":"2507.04742","title":"Activation Steering for Chain-of-Thought Compression","created":"2025-07-07","cited_by_count":24},{"id":"2507.03704","title":"Controlling Thinking Speed in Reasoning Models","created":"2025-07-04","cited_by_count":10},{"id":"2506.20160","title":"AALC: Large Language Model Efficient Reasoning via Adaptive Accuracy-Length Control","created":"2025-06-25","cited_by_count":11},{"id":"2506.15882","title":"Fractional Reasoning via Latent Steering Vectors Improves Inference Time Compute","created":"2025-06-18","cited_by_count":14},{"id":"2506.14755","title":"Optimizing Length Compression in Large Reasoning Models","created":"2025-06-17","cited_by_count":38},{"id":"2506.12353","title":"Efficient Reasoning Through Suppression of Self-Affirmation Reflections in Large Reasoning Models","created":"2025-06-14","cited_by_count":10},{"id":"2506.10822","title":"ReCUT: Balancing Reasoning Length and Accuracy in LLMs via Stepwise Trails and Preference Optimization","created":"2025-06-12","cited_by_count":14},{"id":"2506.10446","title":"Fast on the Easy, Deep on the Hard: Efficient Reasoning via Powered Length Penalty","created":"2025-06-12","cited_by_count":15},{"id":"2506.08390","title":"On Reasoning Strength Planning in Large Reasoning Models","created":"2025-06-10","cited_by_count":13},{"id":"2506.08343","title":"Wait, We Don't Need to \"Wait\"! Removing Thinking Tokens Improves Reasoning Efficiency","created":"2025-06-10","cited_by_count":66},{"id":"2506.08125","title":"Not All Tokens Matter: Towards Efficient LLM Reasoning via Token Significance in Reinforcement Learning","created":"2025-06-09","cited_by_count":10},{"id":"2506.07240","title":"Overclocking LLM Reasoning: Monitoring and Controlling Thinking Path Lengths in LLMs","created":"2025-06-08","cited_by_count":22},{"id":"2506.07104","title":"How Far Are We from Optimal Reasoning Efficiency?","created":"2025-06-08","cited_by_count":8},{"id":"2506.06998","title":"What makes Reasoning Models Different? Follow the Reasoning Leader for Efficient Decoding","created":"2025-06-08","cited_by_count":8},{"id":"2506.05901","title":"Route-and-Reason: Scaling Large Language Model Reasoning with Reinforced Model Router","created":"2025-06-06","cited_by_count":13},{"id":"2506.05745","title":"SPRINT: Enabling Interleaved Planning and Parallelized Execution in Reasoning Models","created":"2025-06-06","cited_by_count":10},{"id":"2506.05256","title":"Just Enough Thinking: Efficient Reasoning with Adaptive Length Penalties Reinforcement Learning","created":"2025-06-05","cited_by_count":52},{"id":"2506.02397","title":"OThink-R1: Intrinsic Fast/Slow Thinking Mode Switching for Over-Reasoning Mitigation","created":"2025-06-03","cited_by_count":17},{"id":"2505.24550","title":"A*-Thought: Efficient Reasoning via Bidirectional Compression for Low-Resource Settings","created":"2025-05-30","cited_by_count":9},{"id":"2505.22662","title":"AutoL2S: Auto Long-Short Reasoning for Efficient Large Language Models","created":"2025-05-28","cited_by_count":12},{"id":"2505.22411","title":"Mitigating Overthinking in Large Reasoning Models via Manifold Steering","created":"2025-05-28","cited_by_count":33},{"id":"2505.22017","title":"The Price of a Second Thought: On the Evaluation of Reasoning Efficiency in Large Language Models","created":"2025-05-28","cited_by_count":18},{"id":"2505.21765","title":"Don't Think Longer, Think Wisely: Optimizing Thinking Dynamics for Large Reasoning Models","created":"2025-05-27","cited_by_count":11},{"id":"2505.21600","title":"R2R: Efficiently Navigating Divergent Reasoning Paths with Small-Large Model Token Routing","created":"2025-05-27","cited_by_count":29},{"id":"2505.21097","title":"Thinker: Learning to Think Fast and Slow","created":"2025-05-27","cited_by_count":10},{"id":"2505.20664","title":"Self-Route: Automatic Mode Switching via Capability Estimation for Efficient Reasoning","created":"2025-05-27","cited_by_count":8},{"id":"2505.20101","title":"Adaptive Deep Reasoning: Triggering Deep Thinking When Needed","created":"2025-05-26","cited_by_count":14},{"id":"2505.19788","title":"Done Is Better than Perfect: Unlocking Efficient Reasoning by Structured Multi-Turn Decomposition","created":"2025-05-26","cited_by_count":11},{"id":"2505.19640","title":"Interleaved Reasoning for Large Language Models via Reinforcement Learning","created":"2025-05-26","cited_by_count":21},{"id":"2505.19435","title":"Route to Reason: Adaptive Routing for LLM and Reasoning Strategy Selection","created":"2025-05-26","cited_by_count":23},{"id":"2505.19187","title":"LIMOPro: Reasoning Refinement for Efficient and Effective Test-time Scaling","created":"2025-05-25","cited_by_count":15},{"id":"2505.18822","title":"AdaCtrl: Towards Adaptive and Controllable Reasoning via Difficulty-Aware Budgeting","created":"2025-05-24","cited_by_count":50},{"id":"2505.20325","title":"Guided by Gut: Efficient Test-Time Scaling with Reinforced Intrinsic Confidence","created":"2025-05-23","cited_by_count":8},{"id":"2505.18298","title":"Thinking Fast and Right: Balancing Accuracy and Reasoning Length with Adaptive Rewards","created":"2025-05-23","cited_by_count":20},{"id":"2505.18237","title":"Think or Not? Exploring Thinking Efficiency in Large Reasoning Models via an Information-Theoretic Lens","created":"2025-05-23","cited_by_count":34},{"id":"2505.18149","title":"First Finish Search: Efficient Test-Time Scaling in Large Language Models","created":"2025-05-23","cited_by_count":9},{"id":"2505.17941","title":"VeriThinker: Learning to Verify Makes Reasoning Model Efficient","created":"2025-05-23","cited_by_count":24},{"id":"2505.17827","title":"Not All Tokens Are What You Need In Thinking","created":"2025-05-23","cited_by_count":20},{"id":"2505.17813","title":"Don't Overthink it. Preferring Shorter Thinking Chains for Improved LLM Reasoning","created":"2025-05-23","cited_by_count":85},{"id":"2505.17155","title":"TrimR: Verifier-based Training-Free Thinking Compression for Efficient Test-Time Scaling","created":"2025-05-22","cited_by_count":14},{"id":"2505.16838","title":"R1-Compress: Long Chain-of-Thought Compression via Chunk Compression and Search","created":"2025-05-22","cited_by_count":30},{"id":"2505.16315","title":"Incentivizing Dual Process Thinking for Efficient Large Language Model Reasoning","created":"2025-05-22","cited_by_count":21},{"id":"2505.16122","title":"Plan and Budget: Effective and Efficient Test-Time Scaling on Reasoning Large Language Models","created":"2025-05-22","cited_by_count":32},{"id":"2505.15612","title":"Learn to Reason Efficiently with Adaptive Length-based Reward Shaping","created":"2025-05-21","cited_by_count":75},{"id":"2505.15154","title":"Prolonged Reasoning Is Not All You Need: Certainty-Based Adaptive Routing for Efficient LLM/MLLM Reasoning","created":"2025-05-21","cited_by_count":35},{"id":"2505.14631","title":"Think Only When You Need with Large Hybrid-Reasoning Models","created":"2025-05-20","cited_by_count":66},{"id":"2505.14582","title":"Can Pruning Improve Reasoning? Revisiting Long-CoT Compression with Capability in Mind for Better Reasoning","created":"2025-05-20","cited_by_count":19},{"id":"2505.14183","title":"ThinkSwitcher: When to Think Hard, When to Think Fast","created":"2025-05-20","cited_by_count":37},{"id":"2505.13949","title":"FlashThink: An Early Exit Method For Efficient Reasoning","created":"2025-05-20","cited_by_count":28},{"id":"2505.13866","title":"Reasoning Path Compression: Compressing Generation Trajectories for Efficient LLM Reasoning","created":"2025-05-20","cited_by_count":17},{"id":"2505.13438","title":"Optimizing Anytime Reasoning via Budget Relative Policy Optimization","created":"2025-05-19","cited_by_count":27},{"id":"2505.13417","title":"AdaptThink: Reasoning Models Can Learn When to Think","created":"2025-05-19","cited_by_count":147},{"id":"2505.13379","title":"Thinkless: LLM Learns When to Think","created":"2025-05-19","cited_by_count":113},{"id":"2505.12284","title":"Shorten After You're Right: Lazy Length Penalties for Reasoning RL","created":"2025-05-18","cited_by_count":25},{"id":"2505.11896","title":"AdaCoT: Pareto-Optimal Adaptive Chain-of-Thought Triggering via Reinforcement Learning","created":"2025-05-17","cited_by_count":87},{"id":"2505.11827","title":"Not All Thoughts are Generated Equal: Efficient LLM Reasoning via Multi-Turn Reinforcement Learning","created":"2025-05-17","cited_by_count":16},{"id":"2505.11274","title":"SelfBudgeter: Adaptive Token Allocation for Efficient LLM Reasoning","created":"2025-05-16","cited_by_count":48},{"id":"2505.10832","title":"Learning When to Think: Shaping Adaptive Reasoning in R1-Style Models via Multi-Stage RL","created":"2025-05-16","cited_by_count":62},{"id":"2505.08392","title":"Adaptive GoGI-Skip: Coupling Goal-Gradient Importance with Dynamic Uncertainty for Efficient Reasoning","created":"2025-05-13","cited_by_count":12},{"id":"2505.05315","title":"Scalable Chain of Thoughts via Elastic Reasoning","created":"2025-05-08","cited_by_count":34},{"id":"2505.04881","title":"ConCISE: Confidence-guided Compression in Step-by-step Efficient Reasoning","created":"2025-05-08","cited_by_count":33},{"id":"2505.03469","title":"Long-Short Chain-of-Thought Mixture Supervised Fine-Tuning Eliciting Efficient Reasoning in Large Language Models","created":"2025-05-06","cited_by_count":39},{"id":"2505.02865","title":"Accelerating Large Language Model Reasoning via Speculative Search","created":"2025-05-03","cited_by_count":16},{"id":"2504.21370","title":"ShorterBetter: Guiding Reasoning Models to Find Optimal Inference Length for Efficient Reasoning","created":"2025-04-30","cited_by_count":72},{"id":"2504.19095","title":"Efficient Reasoning for LLMs through Speculative Chain-of-Thought","created":"2025-04-27","cited_by_count":22},{"id":"2504.16379","title":"SplitReason: Learning To Offload Reasoning","created":"2025-04-23","cited_by_count":11},{"id":"2504.15895","title":"Dynamic Early Exit in Reasoning Models","created":"2025-04-22","cited_by_count":219},{"id":"2504.13626","title":"Thought Manipulation: External Thought Can Be Efficient for Large Reasoning Models","created":"2025-04-18","cited_by_count":23},{"id":"2504.10903","title":"Efficient Reasoning Models: A Survey","created":"2025-04-15","cited_by_count":95},{"id":"2504.12329","title":"Speculative Thinking: Enhancing Small-Model Reasoning with Large Model Guidance at Inference Time","created":"2025-04-12","cited_by_count":48},{"id":"2504.07891","title":"SpecReason: Fast and Accurate Inference-Time Compute via Speculative Reasoning","created":"2025-04-10","cited_by_count":59},{"id":"2504.07986","title":"SEAL: Steerable Reasoning Calibration of Large Language Models for Free","created":"2025-04-07","cited_by_count":68},{"id":"2504.05419","title":"Reasoning Models Know When They're Right: Probing Hidden States for Self-Verification","created":"2025-04-07","cited_by_count":159},{"id":"2504.01296","title":"ThinkPrune: Pruning Long Chain-of-Thought of LLMs via Reinforcement Learning","created":"2025-04-02","cited_by_count":192},{"id":"2504.00424","title":"Hawkeye:Efficient Reasoning with Model Collaboration","created":"2025-04-01","cited_by_count":11},{"id":"2503.24377","title":"Harnessing the Reasoning Economy: A Survey of Efficient Reasoning for Large Language Models","created":"2025-03-31","cited_by_count":36},{"id":"2503.23077","title":"Efficient Inference for Large Reasoning Models: A Survey","created":"2025-03-29","cited_by_count":61},{"id":"2503.21614","title":"A Survey of Efficient Reasoning for Large Reasoning Models: Language, Multimodality, and Beyond","created":"2025-03-27","cited_by_count":132},{"id":"2503.20641","title":"Unlocking Efficient Long-to-Short LLM Reasoning with Model Merging","created":"2025-03-26","cited_by_count":58},{"id":"2503.16419","title":"Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models","created":"2025-03-20","cited_by_count":464},{"id":"2503.04697","title":"L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learning","created":"2025-03-06","cited_by_count":384},{"id":"2503.04472","title":"DAST: Difficulty-Adaptive Slow-Thinking for Large Reasoning Models","created":"2025-03-06","cited_by_count":158},{"id":"2503.01141","title":"How Well do LLMs Compress Their Own Chain-of-Thought? A Token Complexity Approach","created":"2025-03-03","cited_by_count":97},{"id":"2502.20122","title":"Self-Training Elicits Concise Reasoning in Large Language Models","created":"2025-02-27","cited_by_count":99},{"id":"2502.12067","title":"TokenSkip: Controllable Chain-of-Thought Compression in LLMs","created":"2025-02-17","cited_by_count":249},{"id":"2502.09601","title":"CoT-Valve: Length-Compressible Chain-of-Thought Tuning","created":"2025-02-13","cited_by_count":169},{"id":"2502.08235","title":"The Danger of Overthinking: Examining the Reasoning-Action Dilemma in Agentic Tasks","created":"2025-02-12","cited_by_count":152},{"id":"2501.19324","title":"Reward-Guided Speculative Decoding for Efficient LLM Reasoning","created":"2025-01-31","cited_by_count":106},{"id":"2501.18585","title":"Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs","created":"2025-01-30","cited_by_count":163},{"id":"2501.12570","title":"O1-Pruner: Length-Harmonizing Fine-Tuning for O1-Like Reasoning Pruning","created":"2025-01-22","cited_by_count":279},{"id":"2412.21187","title":"Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs","created":"2024-12-30","cited_by_count":570},{"id":"2412.18547","title":"Token-Budget-Aware LLM Reasoning","created":"2024-12-24","cited_by_count":247},{"id":"2411.14405","title":"Marco-o1: Towards Open Reasoning Models for Open-Ended Solutions","created":"2024-11-21","cited_by_count":144},{"id":"2407.19825","title":"Concise Thoughts: Impact of Output Length on LLM Reasoning and Cost","created":"2024-07-29","cited_by_count":109},{"id":"2401.01879","title":"Theoretical guarantees on the best-of-n alignment policy","created":"2024-01-03","cited_by_count":124}],"next_cursor":null}