{"list":"closest","total":54,"rows":[{"id":"2504.10449","title":"M1: Towards Scalable Test-Time Compute with Mamba Reasoning Models","created":"2025-04-14","cited_by_count":21},{"id":"2504.07891","title":"SpecReason: Fast and Accurate Inference-Time Compute via Speculative Reasoning","created":"2025-04-10","cited_by_count":59},{"id":"2504.04823","title":"Quantization Hurts Reasoning? An Empirical Study on Quantized Reasoning Models","created":"2025-04-07","cited_by_count":73},{"id":"2504.01296","title":"ThinkPrune: Pruning Long Chain-of-Thought of LLMs via Reinforcement Learning","created":"2025-04-02","cited_by_count":192},{"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":"2503.13288","title":"$\\phi$-Decoding: Adaptive Foresight Sampling for Balanced Inference-Time Exploration and Exploitation","created":"2025-03-17","cited_by_count":13},{"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":"2503.01422","title":"Sampling-Efficient Test-Time Scaling: Self-Estimating the Best-of-N Sampling in Early Decoding","created":"2025-03-03","cited_by_count":63},{"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":"2502.20122","title":"Self-Training Elicits Concise Reasoning in Large Language Models","created":"2025-02-27","cited_by_count":99},{"id":"2502.19918","title":"Meta-Reasoner: Dynamic Guidance for Optimized Inference-time Reasoning in Large Language Models","created":"2025-02-27","cited_by_count":33},{"id":"2503.00031","title":"Efficient Test-Time Scaling via Self-Calibration","created":"2025-02-25","cited_by_count":75},{"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":"2502.16235","title":"Dynamic Parallel Tree Search for Efficient LLM Reasoning","created":"2025-02-22","cited_by_count":42},{"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":"2502.12018","title":"Atom of Thoughts for Markov LLM Test-Time Scaling","created":"2025-02-17","cited_by_count":54},{"id":"2502.11476","title":"FastMCTS: A Simple Sampling Strategy for Data Synthesis","created":"2025-02-17","cited_by_count":17},{"id":"2502.11183","title":"Don't Get Lost in the Trees: Streamlining LLM Reasoning by Overcoming Tree Search Exploration Pitfalls","created":"2025-02-16","cited_by_count":13},{"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":"2502.07191","title":"Bag of Tricks for Inference-time Computation of LLM Reasoning","created":"2025-02-11","cited_by_count":15},{"id":"2502.06703","title":"Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling","created":"2025-02-10","cited_by_count":136},{"id":"2502.06233","title":"Confidence Improves Self-Consistency in LLMs","created":"2025-02-10","cited_by_count":113},{"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":"2502.00511","title":"Bridging Internal Probability and Self-Consistency for Effective and Efficient LLM Reasoning","created":"2025-02-01","cited_by_count":18},{"id":"2501.19393","title":"s1: Simple test-time scaling","created":"2025-01-31","cited_by_count":1341},{"id":"2501.19324","title":"Reward-Guided Speculative Decoding for Efficient LLM Reasoning","created":"2025-01-31","cited_by_count":106},{"id":"2501.19201","title":"Efficient Reasoning with Hidden Thinking","created":"2025-01-31","cited_by_count":75},{"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":"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":"2408.17017","title":"Reasoning Aware Self-Consistency: Leveraging Reasoning Paths for Efficient LLM Sampling","created":"2024-08-30","cited_by_count":63},{"id":"2409.01281","title":"Path-Consistency with Prefix Enhancement for Efficient Inference in LLMs","created":"2024-08-25","cited_by_count":17},{"id":"2408.13457","title":"Make Every Penny Count: Difficulty-Adaptive Self-Consistency for Cost-Efficient Reasoning","created":"2024-08-24","cited_by_count":63},{"id":"2408.03314","title":"Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters","created":"2024-08-06","cited_by_count":1986},{"id":"2406.11698","title":"Meta Reasoning for Large Language Models","created":"2024-06-17","cited_by_count":29},{"id":"2404.17140","title":"Small Language Models Need Strong Verifiers to Self-Correct Reasoning","created":"2024-04-26","cited_by_count":86},{"id":"2401.10480","title":"Escape Sky-high Cost: Early-stopping Self-Consistency for Multi-step Reasoning","created":"2024-01-19","cited_by_count":108},{"id":"2307.15337","title":"Skeleton-of-Thought: Prompting LLMs for Efficient Parallel Generation","created":"2023-07-28","cited_by_count":105},{"id":"2305.11860","title":"Let's Sample Step by Step: Adaptive-Consistency for Efficient Reasoning and Coding with LLMs","created":"2023-05-19","cited_by_count":115},{"id":"2305.11738","title":"CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquing","created":"2023-05-19","cited_by_count":783},{"id":"2305.10601","title":"Tree of Thoughts: Deliberate Problem Solving with Large Language Models","created":"2023-05-17","cited_by_count":3211},{"id":"2303.17651","title":"Self-Refine: Iterative Refinement with Self-Feedback","created":"2023-03-30","cited_by_count":3442}],"next_cursor":null}