{"total":59,"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":"2502.12067","title":"TokenSkip: Controllable Chain-of-Thought Compression in LLMs","created":"2025-02-17","cited_by_count":249,"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":"2503.21614","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":"2502.15589","title":"LightThinker: Thinking Step-by-Step Compression","created":"2025-02-21","cited_by_count":104,"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":"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":"2508.03346","title":"Making Slow Thinking Faster: Compressing LLM Chain-of-Thought via Step Entropy","created":"2025-08-05","cited_by_count":38,"area":"lr"},{"id":"2504.13367","title":"THOUGHTTERMINATOR: Benchmarking, Calibrating, and Mitigating Overthinking in Reasoning Models","created":"2025-04-17","cited_by_count":35,"area":"lr"},{"id":"2510.15110","title":"DLER: Doing Length pEnalty Right - Incentivizing More Intelligence per Token via Reinforcement Learning","created":"2025-10-16","cited_by_count":35,"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":"2503.15848","title":"Entropy-based Exploration Conduction for Multi-step Reasoning","created":"2025-03-20","cited_by_count":29,"area":"lr"},{"id":"2505.18962","title":"System-1.5 Reasoning: Traversal in Language and Latent Spaces with Dynamic Shortcuts","created":"2025-05-25","cited_by_count":27,"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":"2507.20198","title":"A Survey of Token Compression for Efficient Multimodal Large Language Models","created":"2025-07-27","cited_by_count":25,"area":"mllm"},{"id":"2505.17941","title":"VeriThinker: Learning to Verify Makes Reasoning Model Efficient","created":"2025-05-23","cited_by_count":24,"area":"lr"},{"id":"2504.13626","title":"Thought Manipulation: External Thought Can Be Efficient for Large Reasoning Models","created":"2025-04-18","cited_by_count":23,"area":"lr"},{"id":"2505.16826","title":"KTAE: A Model-Free Algorithm to Key-Tokens Advantage Estimation in Mathematical Reasoning","created":"2025-05-22","cited_by_count":19,"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":"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":"2504.13828","title":"Generative AI Act II: Test Time Scaling Drives Cognition Engineering","created":"2025-04-18","cited_by_count":15,"area":"lr"},{"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,"area":"lr"},{"id":"2506.07851","title":"Learning to Focus: Causal Attention Distillation via Gradient-Guided Token Pruning","created":"2025-06-09","cited_by_count":13,"area":"inference"},{"id":"2505.22662","title":"AutoL2S: Auto Long-Short Reasoning for Efficient Large Language Models","created":"2025-05-28","cited_by_count":12,"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":"2506.04182","title":"Long or short CoT? Investigating Instance-level Switch of Large Reasoning Models","created":"2025-06-04","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":"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":"2510.11713","title":"Are Large Reasoning Models Interruptible?","created":"2025-10-13","cited_by_count":7,"area":"lr"},{"id":"2505.17746","title":"Fast Quiet-STaR: Thinking Without Thought Tokens","created":"2025-05-23","cited_by_count":5,"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":"2511.13223","title":"TokenSqueeze: Performance-Preserving Compression for Reasoning LLMs","created":"2025-11-17","cited_by_count":5,"area":"lr"},{"id":"2412.21006","title":"Verbosity-Aware Rationale Reduction: Effective Reduction of Redundant Rationale via Principled Criteria","created":"2024-12-30","cited_by_count":4,"area":null},{"id":"2509.23967","title":"HiPO: Hybrid Policy Optimization for Dynamic Reasoning in LLMs","created":"2025-09-28","cited_by_count":4,"area":"lr"},{"id":"2510.13170","title":"Putting on the Thinking Hats: A Survey on Chain of Thought Fine-tuning from the Perspective of Human Reasoning Mechanism","created":"2025-10-15","cited_by_count":4,"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":"2506.14794","title":"Assembly of Experts: Linear-time construction of the Chimera LLM variants with emergent and adaptable behaviors","created":"2025-05-31","cited_by_count":3,"area":null},{"id":"2606.01243","title":"Unlocking the Black Box of Latent Reasoning: An Interpretability-Guided Approach to Intervention","created":"2026-05-31","cited_by_count":3,"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":"2510.01030","title":"Uncovering the Computational Ingredients of Human-Like Representations in LLMs","created":"2025-10-01","cited_by_count":1,"area":null},{"id":"2601.22617","title":"EntroCut: Entropy-Guided Adaptive Truncation for Efficient Chain-of-Thought Reasoning in Small-scale Large Reasoning Models","created":"2026-01-30","cited_by_count":1,"area":"lr"},{"id":"2602.02909","title":"Reasoning about Reasoning: BAPO Bounds on Chain-of-Thought Token Complexity in LLMs","created":"2026-02-02","cited_by_count":1,"area":"lr"},{"id":"2603.07598","title":"SCA: Segment-Wise CoT Compression with Answer Alignment","created":"2026-03-08","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":"2606.20937","title":"Learning through Internalization","created":"2026-06-18","cited_by_count":1,"area":null},{"id":"2602.12526","title":"Constraint-Rectified Training for Efficient Chain-of-Thought","created":"2026-02-13","cited_by_count":0,"area":"lr"},{"id":"2605.01111","title":"When Less is Enough: Efficient Inference via Collaborative Reasoning","created":"2026-05-01","cited_by_count":0,"area":null},{"id":"2606.01168","title":"Thinking Economically: A Hierarchical Framework for Adaptive-Complexity Reasoning in LLMs","created":"2026-05-31","cited_by_count":0,"area":"lr"},{"id":"2607.19358","title":"LISA: Linear-Indexed Sparse Attention for Efficient Long-Context Reasoning","created":"2026-05-29","cited_by_count":0,"area":"lr"}],"next_cursor":null}