{"total":106,"rows":[{"id":"2503.16419","title":"Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models","created":"2025-03-20","cited_by_count":464,"area":"lr"},{"id":"2503.04697","title":"L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learning","created":"2025-03-06","cited_by_count":384,"area":"lr"},{"id":"2502.17419","title":"From System 1 to System 2: A Survey of Reasoning Large Language Models","created":"2025-02-24","cited_by_count":320,"area":"lr"},{"id":"2501.12570","title":"O1-Pruner: Length-Harmonizing Fine-Tuning for O1-Like Reasoning Pruning","created":"2025-01-22","cited_by_count":279,"area":"lr"},{"id":"2502.12067","title":"TokenSkip: Controllable Chain-of-Thought Compression in LLMs","created":"2025-02-17","cited_by_count":249,"area":"lr"},{"id":"2502.04463","title":"Training Language Models to Reason Efficiently","created":"2025-02-06","cited_by_count":247,"area":"lr"},{"id":"2504.15895","title":"Dynamic Early Exit in Reasoning Models","created":"2025-04-22","cited_by_count":219,"area":"lr"},{"id":"2504.09858","title":"Reasoning Models Can Be Effective Without Thinking","created":"2025-04-14","cited_by_count":187,"area":"lr"},{"id":"2502.09601","title":"CoT-Valve: Length-Compressible Chain-of-Thought Tuning","created":"2025-02-13","cited_by_count":169,"area":"lr"},{"id":"2503.04472","title":"DAST: Difficulty-Adaptive Slow-Thinking for Large Reasoning Models","created":"2025-03-06","cited_by_count":158,"area":"lr"},{"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,"area":"lr"},{"id":"2504.16828","title":"Process Reward Models That Think","created":"2025-04-23","cited_by_count":118,"area":"lr"},{"id":"2505.13379","title":"Thinkless: LLM Learns When to Think","created":"2025-05-19","cited_by_count":113,"area":"lr"},{"id":"2502.15589","title":"LightThinker: Thinking Step-by-Step Compression","created":"2025-02-21","cited_by_count":104,"area":"lr"},{"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,"area":"lr"},{"id":"2503.22342","title":"CPPO: Accelerating the Training of Group Relative Policy Optimization-Based Reasoning Models","created":"2025-03-28","cited_by_count":96,"area":"lr"},{"id":"2504.10903","title":"Efficient Reasoning Models: A Survey","created":"2025-04-15","cited_by_count":95,"area":"lr"},{"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":"2505.11896","title":"AdaCoT: Pareto-Optimal Adaptive Chain-of-Thought Triggering via Reinforcement Learning","created":"2025-05-17","cited_by_count":87,"area":"lr"},{"id":"2505.17813","title":"Don't Overthink it. Preferring Shorter Thinking Chains for Improved LLM Reasoning","created":"2025-05-23","cited_by_count":85,"area":"lr"},{"id":"2503.23077","title":"Efficient Inference for Large Reasoning Models: A Survey","created":"2025-03-29","cited_by_count":61,"area":"lr"},{"id":"2503.06692","title":"InftyThink: Breaking the Length Limits of Long-Context Reasoning in Large Language Models","created":"2025-03-09","cited_by_count":54,"area":"lr"},{"id":"2505.18822","title":"AdaCtrl: Towards Adaptive and Controllable Reasoning via Difficulty-Aware Budgeting","created":"2025-05-24","cited_by_count":50,"area":"lr"},{"id":"2505.11274","title":"SelfBudgeter: Adaptive Token Allocation for Efficient LLM Reasoning","created":"2025-05-16","cited_by_count":48,"area":"lr"},{"id":"2501.02497","title":"A Survey of Test-Time Compute: From Intuitive Inference to Deliberate Reasoning","created":"2025-01-05","cited_by_count":40,"area":"lr"},{"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,"area":"lr"},{"id":"2505.14183","title":"ThinkSwitcher: When to Think Hard, When to Think Fast","created":"2025-05-20","cited_by_count":37,"area":"lr"},{"id":"2508.13141","title":"OptimalThinkingBench: Evaluating Over and Underthinking in LLMs","created":"2025-08-18","cited_by_count":35,"area":"lr"},{"id":"2505.05315","title":"Scalable Chain of Thoughts via Elastic Reasoning","created":"2025-05-08","cited_by_count":34,"area":"lr"},{"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,"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":"2505.14604","title":"Let LRMs Break Free from Overthinking via Self-Braking Tuning","created":"2025-05-20","cited_by_count":27,"area":"lr"},{"id":"2505.15400","title":"When to Continue Thinking: Adaptive Thinking Mode Switching for Efficient Reasoning","created":"2025-05-21","cited_by_count":26,"area":"lr"},{"id":"2505.12284","title":"Shorten After You're Right: Lazy Length Penalties for Reasoning RL","created":"2025-05-18","cited_by_count":25,"area":"lr"},{"id":"2505.19435","title":"Route to Reason: Adaptive Routing for LLM and Reasoning Strategy Selection","created":"2025-05-26","cited_by_count":23,"area":"lr"},{"id":"2505.17827","title":"Not All Tokens Are What You Need In Thinking","created":"2025-05-23","cited_by_count":20,"area":"lr"},{"id":"2505.18298","title":"Thinking Fast and Right: Balancing Accuracy and Reasoning Length with Adaptive Rewards","created":"2025-05-23","cited_by_count":20,"area":"lr"},{"id":"2508.08940","title":"Train Long, Think Short: Curriculum Learning for Efficient Reasoning","created":"2025-08-12","cited_by_count":20,"area":"lr"},{"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,"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":"2604.09852","title":"MEMENTO: Teaching LLMs to Manage Their Own Context","created":"2026-04-10","cited_by_count":18,"area":"lr"},{"id":"2506.02397","title":"OThink-R1: Intrinsic Fast/Slow Thinking Mode Switching for Over-Reasoning Mitigation","created":"2025-06-03","cited_by_count":17,"area":"lr"},{"id":"2506.09853","title":"Causal Sufficiency and Necessity Improves Chain-of-Thought Reasoning","created":"2025-06-11","cited_by_count":17,"area":"lr"},{"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,"area":"lr"},{"id":"2506.02678","title":"TL;DR: Too Long, Do Re-weighting for Efficient LLM Reasoning Compression","created":"2025-06-03","cited_by_count":16,"area":"lr"},{"id":"2504.13828","title":"Generative AI Act II: Test Time Scaling Drives Cognition Engineering","created":"2025-04-18","cited_by_count":15,"area":"lr"},{"id":"2505.20101","title":"Adaptive Deep Reasoning: Triggering Deep Thinking When Needed","created":"2025-05-26","cited_by_count":14,"area":"lr"},{"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,"area":"lr"},{"id":"2506.23840","title":"Do Thinking Tokens Help or Trap? Towards More Efficient Large Reasoning Model","created":"2025-06-30","cited_by_count":14,"area":"lr"},{"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,"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":"2509.18639","title":"Understanding-in-Generation: Reinforcing Generative Capability of Unified Model via Infusing Understanding into Generation","created":"2025-09-23","cited_by_count":11,"area":"lr"},{"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,"area":"lr"},{"id":"2510.08483","title":"DeepPrune: Parallel Scaling without Inter-trace Redundancy","created":"2025-10-09","cited_by_count":10,"area":"lr"},{"id":"2601.23184","title":"ReGuLaR: Variational Latent Reasoning Guided by Rendered Chain-of-Thought","created":"2026-01-30","cited_by_count":10,"area":"lr"},{"id":"2505.19217","title":"The Overthinker's DIET: Cutting Token Calories with DIfficulty-AwarE Training","created":"2025-05-25","cited_by_count":9,"area":"lr"},{"id":"2510.10494","title":"Tracing the Traces: Latent Temporal Signals for Efficient and Accurate Reasoning","created":"2025-10-12","cited_by_count":9,"area":"lr"},{"id":"2602.08332","title":"Latent Reasoning with Supervised Thinking States","created":"2026-02-09","cited_by_count":9,"area":"lr"},{"id":"2505.20664","title":"Self-Route: Automatic Mode Switching via Capability Estimation for Efficient Reasoning","created":"2025-05-27","cited_by_count":8,"area":"lr"},{"id":"2505.23701","title":"Can LLMs Reason Abstractly Over Math Word Problems Without CoT? Disentangling Abstract Formulation From Arithmetic Computation","created":"2025-05-29","cited_by_count":8,"area":"lr"},{"id":"2506.07104","title":"How Far Are We from Optimal Reasoning Efficiency?","created":"2025-06-08","cited_by_count":8,"area":"lr"},{"id":"2506.15647","title":"Exploring and Exploiting the Inherent Efficiency within Large Reasoning Models for Self-Guided Efficiency Enhancement","created":"2025-06-18","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":"2604.02967","title":"FoE: Forest of Errors Makes the First Solution the Best in Large Reasoning Models","created":"2026-04-03","cited_by_count":8,"area":"lr"},{"id":"2505.19756","title":"Efficient Reasoning via Chain of Unconscious Thought","created":"2025-05-26","cited_by_count":7,"area":"lr"},{"id":"2508.17291","title":"Meta-R1: Empowering Large Reasoning Models with Metacognition","created":"2025-08-24","cited_by_count":6,"area":"lr"},{"id":"2511.00640","title":"DTS: Enhancing Large Reasoning Models via Decoding Tree Sketching","created":"2025-11-01","cited_by_count":6,"area":"lr"},{"id":"2601.21418","title":"Mitigating Overthinking in Large Reasoning Models via Difficulty-aware Reinforcement Learning","created":"2026-01-29","cited_by_count":6,"area":"lr"},{"id":"2601.22582","title":"MC-GRPO: Median-Centered Group Relative Policy Optimization for Small-Rollout Reinforcement Learning","created":"2026-01-30","cited_by_count":6,"area":"lr"},{"id":"2506.10716","title":"PREMISE: Scalable and Strategic Prompt Optimization for Efficient Mathematical Reasoning in Large Models","created":"2025-06-12","cited_by_count":5,"area":"lr"},{"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,"area":"lr"},{"id":"2507.06087","title":"CoRE: Enhancing Metacognition with Label-free Self-evaluation in LRMs","created":"2025-07-08","cited_by_count":5,"area":"lr"},{"id":"2510.15965","title":"One Token Embedding Is Enough to Deadlock Your Large Reasoning Model","created":"2025-10-12","cited_by_count":5,"area":"lr"},{"id":"2511.15392","title":"DEPO: Dual-Efficiency Preference Optimization for LLM Agents","created":"2025-11-19","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":"2604.03679","title":"LightThinker++: From Reasoning Compression to Memory Management","created":"2026-04-04","cited_by_count":4,"area":"lr"},{"id":"2508.10164","title":"Pruning Long Chain-of-Thought of Large Reasoning Models via Small-Scale Preference Optimization","created":"2025-08-13","cited_by_count":3,"area":"lr"},{"id":"2509.21487","title":"Dual-Head Reasoning Distillation: Improving Classifier Accuracy with Train-Time-Only Reasoning","created":"2025-09-25","cited_by_count":3,"area":"lr"},{"id":"2509.25176","title":"SIRI: Scaling Iterative Reinforcement Learning with Interleaved Compression","created":"2025-09-29","cited_by_count":3,"area":"lr"},{"id":"2602.06375","title":"Difficulty-Estimated Policy Optimization","created":"2026-02-06","cited_by_count":3,"area":"lr"},{"id":"2602.21103","title":"Prompt-Level Distillation: A Non-Parametric Alternative to Model Fine-Tuning for Efficient Reasoning","created":"2026-02-24","cited_by_count":3,"area":"lr"},{"id":"2603.00578","title":"Draft-Thinking: Learning Efficient Reasoning in Long Chain-of-Thought LLMs","created":"2026-02-28","cited_by_count":3,"area":"lr"},{"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,"area":"lr"},{"id":"2509.22144","title":"From Long to Lean: Performance-aware and Adaptive Chain-of-Thought Compression via Multi-round Refinement","created":"2025-09-26","cited_by_count":2,"area":"lr"},{"id":"2602.11639","title":"PACE: Prefix-Protected and Difficulty-Aware Compression for Efficient Reasoning","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":"2604.07922","title":"SAT: Balancing Reasoning Accuracy and Efficiency with Stepwise Adaptive Thinking","created":"2026-04-09","cited_by_count":2,"area":"lr"},{"id":"2505.18603","title":"Doc-CoB: Enhancing Document Understanding with Visual Chain-of-Boxes Reasoning","created":"2025-05-24","cited_by_count":1,"area":"lr"},{"id":"2510.00546","title":"ThinkBrake: Efficient Reasoning via Log-Probability Margin Guided Decoding","created":"2025-10-01","cited_by_count":1,"area":"lr"},{"id":"2601.02825","title":"SketchThinker-R1: Towards Efficient Sketch-Style Reasoning in Large Multimodal Models","created":"2026-01-06","cited_by_count":1,"area":"lr"},{"id":"2601.22730","title":"ImgCoT: Compressing Long Chain of Thought into Compact Visual Tokens for Efficient Reasoning of Large Language Model","created":"2026-01-30","cited_by_count":1,"area":"lr"},{"id":"2604.14847","title":"TrigReason: Trigger-Based Collaboration between Small and Large Reasoning Models","created":"2026-04-16","cited_by_count":1,"area":"lr"},{"id":"2605.08665","title":"Hint Tuning: Less Data Makes Better Reasoners","created":"2026-05-09","cited_by_count":1,"area":"lr"},{"id":"2602.11748","title":"Think Longer to Explore Deeper: Learn to Explore In-Context via Length-Incentivized Reinforcement Learning","created":"2026-02-12","cited_by_count":0,"area":"lr"},{"id":"2602.12526","title":"Constraint-Rectified Training for Efficient Chain-of-Thought","created":"2026-02-13","cited_by_count":0,"area":"lr"},{"id":"2604.14214","title":"CROP: Token-Efficient Reasoning in Large Language Models via Regularized Prompt Optimization","created":"2026-04-08","cited_by_count":0,"area":"lr"},{"id":"2605.14457","title":"Stateful Reasoning via Insight Replay","created":"2026-05-14","cited_by_count":0,"area":"lr"},{"id":"2606.06840","title":"Characterize Then Distill: Mechanistic Reasoning in Large Output Spaces","created":"2026-06-05","cited_by_count":0,"area":"lr"},{"id":"2606.21704","title":"When Compression Helps and When It Hurts: Condition-Aware Analysis of Chain-of-Thought Distillation","created":"2026-06-19","cited_by_count":0,"area":"lr"}],"next_cursor":"100"}