{"list":"closest","total":93,"rows":[{"id":"2507.02663","title":"Think How to Think: Mitigating Overthinking with Autonomous Difficulty Cognition in Large Reasoning Models","created":"2025-07-03","cited_by_count":5},{"id":"2507.02076","title":"Reasoning on a Budget: A Survey of Adaptive and Controllable Test-Time Compute in LLMs","created":"2025-07-02","cited_by_count":31},{"id":"2506.23840","title":"Do Thinking Tokens Help or Trap? Towards More Efficient Large Reasoning Model","created":"2025-06-30","cited_by_count":14},{"id":"2506.19492","title":"Is Long-to-Short a Free Lunch? Investigating Inconsistency and Reasoning Efficiency in LRMs","created":"2025-06-24","cited_by_count":2},{"id":"2506.18810","title":"ConciseHint: Boosting Efficient Reasoning via Continuous Concise Hints during Generation","created":"2025-06-23","cited_by_count":10},{"id":"2506.18183","title":"Reasoning about Uncertainty: Do Reasoning Models Know When They Don't Know?","created":"2025-06-22","cited_by_count":38},{"id":"2506.14755","title":"Optimizing Length Compression in Large Reasoning Models","created":"2025-06-17","cited_by_count":38},{"id":"2506.13752","title":"Steering LLM Thinking with Budget Guidance","created":"2025-06-16","cited_by_count":33},{"id":"2506.13585","title":"MiniMax-M1: Scaling Test-Time Compute Efficiently with Lightning Attention","created":"2025-06-16","cited_by_count":263},{"id":"2506.12860","title":"QFFT, Question-Free Fine-Tuning for Adaptive Reasoning","created":"2025-06-15","cited_by_count":15},{"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":"2506.07240","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":"2506.05256","title":"Just Enough Thinking: Efficient Reasoning with Adaptive Length Penalties Reinforcement Learning","created":"2025-06-05","cited_by_count":52},{"id":"2506.04210","title":"Does Thinking More always Help? Mirage of Test-Time Scaling in Reasoning Models","created":"2025-06-04","cited_by_count":53},{"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":"2505.24863","title":"AlphaOne: Reasoning Models Thinking Slow and Fast at Test Time","created":"2025-05-30","cited_by_count":29},{"id":"2505.22411","title":"Mitigating Overthinking in Large Reasoning Models via Manifold Steering","created":"2025-05-28","cited_by_count":33},{"id":"2505.22113","title":"THINK-Bench: Evaluating Thinking Efficiency and Chain-of-Thought Quality of Large Reasoning Models","created":"2025-05-28","cited_by_count":19},{"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":"2505.19435","title":"Route to Reason: Adaptive Routing for LLM and Reasoning Strategy Selection","created":"2025-05-26","cited_by_count":23},{"id":"2505.19217","title":"The Overthinker's DIET: Cutting Token Calories with DIfficulty-AwarE Training","created":"2025-05-25","cited_by_count":9},{"id":"2505.18822","title":"AdaCtrl: Towards Adaptive and Controllable Reasoning via Difficulty-Aware Budgeting","created":"2025-05-24","cited_by_count":50},{"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":"2505.17941","title":"VeriThinker: Learning to Verify Makes Reasoning Model Efficient","created":"2025-05-23","cited_by_count":24},{"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":"2505.16552","title":"Think Silently, Think Fast: Dynamic Latent Compression of LLM Reasoning Chains","created":"2025-05-22","cited_by_count":85},{"id":"2505.16448","title":"The First Impression Problem: Internal Bias Triggers Overthinking in Reasoning Models","created":"2025-05-22","cited_by_count":10},{"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":"2505.15431","title":"Hunyuan-TurboS: Advancing Large Language Models through Mamba-Transformer Synergy and Adaptive Chain-of-Thought","created":"2025-05-21","cited_by_count":29},{"id":"2505.15400","title":"When to Continue Thinking: Adaptive Thinking Mode Switching for Efficient Reasoning","created":"2025-05-21","cited_by_count":26},{"id":"2505.15276","title":"When Can Large Reasoning Models Save Thinking? Mechanistic Analysis of Behavioral Divergence in Reasoning","created":"2025-05-21","cited_by_count":7},{"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":"2505.14604","title":"Let LRMs Break Free from Overthinking via Self-Braking Tuning","created":"2025-05-20","cited_by_count":27},{"id":"2505.14183","title":"ThinkSwitcher: When to Think Hard, When to Think Fast","created":"2025-05-20","cited_by_count":37},{"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":"2505.13326","title":"Thinking Short and Right Over Thinking Long: Serving LLM Reasoning Efficiently and Accurately","created":"2025-05-19","cited_by_count":6},{"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":"2505.11274","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":"2505.02665","title":"A Survey of Slow Thinking-based Reasoning LLMs using Reinforced Learning and Inference-time Scaling Law","created":"2025-05-05","cited_by_count":19},{"id":"2505.00127","title":"Between Underthinking and Overthinking: An Empirical Study of Reasoning Length and correctness in LLMs","created":"2025-04-30","cited_by_count":117},{"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":"2504.15895","title":"Dynamic Early Exit in Reasoning Models","created":"2025-04-22","cited_by_count":219},{"id":"2504.14350","title":"An Empirical Study of LLM Reasoning Ability Under Strict Output Length Constraint","created":"2025-04-19","cited_by_count":17},{"id":"2504.13626","title":"Thought Manipulation: External Thought Can Be Efficient for Large Reasoning Models","created":"2025-04-18","cited_by_count":23},{"id":"2504.10449","title":"M1: Towards Scalable Test-Time Compute with Mamba Reasoning Models","created":"2025-04-14","cited_by_count":21},{"id":"2504.09858","title":"Reasoning Models Can Be Effective Without Thinking","created":"2025-04-14","cited_by_count":187},{"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":"2504.04823","title":"Quantization Hurts Reasoning? An Empirical Study on Quantized Reasoning Models","created":"2025-04-07","cited_by_count":73},{"id":"2503.23077","title":"Efficient Inference for Large Reasoning Models: A Survey","created":"2025-03-29","cited_by_count":61},{"id":"2503.20641","title":"Unlocking Efficient Long-to-Short LLM Reasoning with Model Merging","created":"2025-03-26","cited_by_count":58},{"id":"2503.17979","title":"Trade-offs in Large Reasoning Models: An Empirical Analysis of Deliberative and Adaptive Reasoning over Foundational Capabilities","created":"2025-03-23","cited_by_count":20},{"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":"2502.20339","title":"Thinking Slow, Fast: Scaling Inference Compute with Distilled Reasoners","created":"2025-02-27","cited_by_count":22},{"id":"2502.18080","title":"Towards Thinking-Optimal Scaling of Test-Time Compute for LLM Reasoning","created":"2025-02-25","cited_by_count":119},{"id":"2502.17416","title":"Reasoning with Latent Thoughts: On the Power of Looped Transformers","created":"2025-02-24","cited_by_count":240},{"id":"2502.15589","title":"LightThinker: Thinking Step-by-Step Compression","created":"2025-02-21","cited_by_count":104},{"id":"2502.12521","title":"Inference-Time Computations for LLM Reasoning and Planning: A Benchmark and Insights","created":"2025-02-18","cited_by_count":30},{"id":"2502.12215","title":"Revisiting the Test-Time Scaling of o1-like Models: Do they Truly Possess Test-Time Scaling Capabilities?","created":"2025-02-17","cited_by_count":70},{"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":"2502.03373","title":"Demystifying Long Chain-of-Thought Reasoning in LLMs","created":"2025-02-05","cited_by_count":326},{"id":"2502.03275","title":"Token Assorted: Mixing Latent and Text Tokens for Improved Language Model Reasoning","created":"2025-02-05","cited_by_count":91},{"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":"2412.13171","title":"Compressed Chain of Thought: Efficient Reasoning Through Dense Representations","created":"2024-12-17","cited_by_count":201},{"id":"2412.11664","title":"C3oT: Generating Shorter Chain-of-Thought without Compromising Effectiveness","created":"2024-12-16","cited_by_count":119},{"id":"2410.09918","title":"Dualformer: Controllable Fast and Slow Thinking by Learning with Randomized Reasoning Traces","created":"2024-10-13","cited_by_count":43},{"id":"2407.19825","title":"Concise Thoughts: Impact of Output Length on LLM Reasoning and Cost","created":"2024-07-29","cited_by_count":109},{"id":"2406.10400","title":"Self-Reflection Makes Large Language Models Safer, Less Biased, and Ideologically Neutral","created":"2024-06-14","cited_by_count":20}],"next_cursor":null}