{"list":"other","total":187,"rows":[{"id":"2110.14168","title":"Training Verifiers to Solve Math Word Problems","created":"2021-10-27","cited_by_count":10109},{"id":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320},{"id":"1905.11946","title":"EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks","created":"2019-05-28","cited_by_count":6442},{"id":"2501.12948","title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","created":"2025-01-22","cited_by_count":6330},{"id":"2103.03874","title":"Measuring Mathematical Problem Solving With the MATH Dataset","created":"2021-03-05","cited_by_count":5371},{"id":"2412.15115","title":"Qwen2.5 Technical Report","created":"2024-12-19","cited_by_count":4942},{"id":"1803.05457","title":"Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge","created":"2018-03-14","cited_by_count":4886},{"id":"2305.10601","title":"Tree of Thoughts: Deliberate Problem Solving with Large Language Models","created":"2023-05-17","cited_by_count":3211},{"id":"2311.12022","title":"GPQA: A Graduate-Level Google-Proof Q&A Benchmark","created":"2023-11-20","cited_by_count":2879},{"id":"1806.09055","title":"DARTS: Differentiable Architecture Search","created":"2018-06-24","cited_by_count":1798},{"id":"1611.01578","title":"Neural Architecture Search with Reinforcement Learning","created":"2016-11-05","cited_by_count":1499},{"id":"2412.16720","title":"OpenAI o1 System Card","created":"2024-12-21","cited_by_count":1244},{"id":"2501.12599","title":"Kimi k1.5: Scaling Reinforcement Learning with LLMs","created":"2025-01-22","cited_by_count":1210},{"id":"1707.07012","title":"Learning Transferable Architectures for Scalable Image Recognition","created":"2017-07-21","cited_by_count":1101},{"id":"2405.14734","title":"SimPO: Simple Preference Optimization with a Reference-Free Reward","created":"2024-05-23","cited_by_count":963},{"id":"1807.11626","title":"MnasNet: Platform-Aware Neural Architecture Search for Mobile","created":"2018-07-31","cited_by_count":943},{"id":"1802.01548","title":"Regularized Evolution for Image Classifier Architecture Search","created":"2018-02-05","cited_by_count":909},{"id":"2305.14992","title":"Reasoning with Language Model is Planning with World Model","created":"2023-05-24","cited_by_count":861},{"id":"1802.03268","title":"Efficient Neural Architecture Search via Parameter Sharing","created":"2018-02-09","cited_by_count":837},{"id":"1603.06560","title":"Hyperband: A Novel Bandit-Based Approach to Hyperparameter Optimization","created":"2016-03-21","cited_by_count":699},{"id":"1812.00332","title":"ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware","created":"2018-12-02","cited_by_count":673},{"id":"2310.04406","title":"Language Agent Tree Search Unifies Reasoning Acting and Planning in Language Models","created":"2023-10-06","cited_by_count":574},{"id":"2506.01939","title":"Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning","created":"2025-06-02","cited_by_count":559},{"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":"2406.03816","title":"ReST-MCTS*: LLM Self-Training via Process Reward Guided Tree Search","created":"2024-06-06","cited_by_count":344},{"id":"2502.03373","title":"Demystifying Long Chain-of-Thought Reasoning in LLMs","created":"2025-02-05","cited_by_count":326},{"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},{"id":"2506.06941","title":"The Illusion of Thinking: Understanding the Strengths and Limitations of Reasoning Models via the Lens of Problem Complexity","created":"2025-06-07","cited_by_count":302},{"id":"2309.17179","title":"Alphazero-like Tree-Search can Guide Large Language Model Decoding and Training","created":"2023-09-29","cited_by_count":295},{"id":"2501.09686","title":"Towards Large Reasoning Models: A Survey of Reinforced Reasoning with Large Language Models","created":"2025-01-16","cited_by_count":293},{"id":"2501.12570","title":"O1-Pruner: Length-Harmonizing Fine-Tuning for O1-Like Reasoning Pruning","created":"2025-01-22","cited_by_count":279},{"id":"2502.12067","title":"TokenSkip: Controllable Chain-of-Thought Compression in LLMs","created":"2025-02-17","cited_by_count":249},{"id":"2412.18547","title":"Token-Budget-Aware LLM Reasoning","created":"2024-12-24","cited_by_count":247},{"id":"2502.04463","title":"Training Language Models to Reason Efficiently","created":"2025-02-06","cited_by_count":247},{"id":"2305.14078","title":"Large Language Models as Commonsense Knowledge for Large-Scale Task Planning","created":"2023-05-23","cited_by_count":231},{"id":"2305.08291","title":"Large Language Model Guided Tree-of-Thought","created":"2023-05-15","cited_by_count":221},{"id":"2504.15895","title":"Dynamic Early Exit in Reasoning Models","created":"2025-04-22","cited_by_count":219},{"id":"2305.00633","title":"Self-Evaluation Guided Beam Search for Reasoning","created":"2023-05-01","cited_by_count":196},{"id":"2504.01296","title":"ThinkPrune: Pruning Long Chain-of-Thought of LLMs via Reinforcement Learning","created":"2025-04-02","cited_by_count":192},{"id":"1711.00436","title":"Hierarchical Representations for Efficient Architecture Search","created":"2017-11-01","cited_by_count":191},{"id":"2504.09858","title":"Reasoning Models Can Be Effective Without Thinking","created":"2025-04-14","cited_by_count":187},{"id":"2509.08827","title":"A Survey of Reinforcement Learning for Large Reasoning Models","created":"2025-09-10","cited_by_count":180},{"id":"2502.09601","title":"CoT-Valve: Length-Compressible Chain-of-Thought Tuning","created":"2025-02-13","cited_by_count":169},{"id":"2503.04472","title":"DAST: Difficulty-Adaptive Slow-Thinking for Large Reasoning Models","created":"2025-03-06","cited_by_count":158},{"id":"2407.01476","title":"Tree Search for Language Model Agents","created":"2024-07-01","cited_by_count":151},{"id":"2505.13417","title":"AdaptThink: Reasoning Models Can Learn When to Think","created":"2025-05-19","cited_by_count":147},{"id":"2408.06195","title":"Mutual Reasoning Makes Smaller LLMs Stronger Problem-Solvers","created":"2024-08-12","cited_by_count":138},{"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":"2503.07572","title":"Optimizing Test-Time Compute via Meta Reinforcement Fine-Tuning","created":"2025-03-10","cited_by_count":123},{"id":"2412.11664","title":"C3oT: Generating Shorter Chain-of-Thought without Compromising Effectiveness","created":"2024-12-16","cited_by_count":119},{"id":"2502.18080","title":"Towards Thinking-Optimal Scaling of Test-Time Compute for LLM Reasoning","created":"2025-02-25","cited_by_count":119},{"id":"2505.13379","title":"Thinkless: LLM Learns When to Think","created":"2025-05-19","cited_by_count":113},{"id":"2410.20290","title":"Fast Best-of-N Decoding via Speculative Rejection","created":"2024-10-26","cited_by_count":112},{"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":"2501.19324","title":"Reward-Guided Speculative Decoding for Efficient LLM Reasoning","created":"2025-01-31","cited_by_count":106},{"id":"2307.15337","title":"Skeleton-of-Thought: Prompting LLMs for Efficient Parallel Generation","created":"2023-07-28","cited_by_count":105},{"id":"2310.13227","title":"ToolChain*: Efficient Action Space Navigation in Large Language Models with A* Search","created":"2023-10-20","cited_by_count":105},{"id":"2502.15589","title":"LightThinker: Thinking Step-by-Step Compression","created":"2025-02-21","cited_by_count":104},{"id":"2502.20122","title":"Self-Training Elicits Concise Reasoning in Large Language Models","created":"2025-02-27","cited_by_count":99},{"id":"2406.14283","title":"Q*: Improving Multi-step Reasoning for LLMs with Deliberative Planning","created":"2024-06-20","cited_by_count":97},{"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":"2308.04371","title":"Cumulative Reasoning with Large Language Models","created":"2023-08-08","cited_by_count":94},{"id":"2505.07686","title":"S-GRPO: Early Exit via Reinforcement Learning in Reasoning Models","created":"2025-05-12","cited_by_count":87},{"id":"2505.11896","title":"AdaCoT: Pareto-Optimal Adaptive Chain-of-Thought Triggering via Reinforcement Learning","created":"2025-05-17","cited_by_count":87},{"id":"2505.17813","title":"Don't Overthink it. Preferring Shorter Thinking Chains for Improved LLM Reasoning","created":"2025-05-23","cited_by_count":85},{"id":"2504.05185","title":"Concise Reasoning via Reinforcement Learning","created":"2025-04-07","cited_by_count":79},{"id":"2505.15612","title":"Learn to Reason Efficiently with Adaptive Length-based Reward Shaping","created":"2025-05-21","cited_by_count":75},{"id":"2508.09726","title":"Sample More to Think Less: Group Filtered Policy Optimization for Concise Reasoning","created":"2025-08-13","cited_by_count":75},{"id":"2007.08124","title":"LogiQA: A Challenge Dataset for Machine Reading Comprehension with Logical Reasoning","created":"2020-07-16","cited_by_count":69},{"id":"2506.22716","title":"BEST-Route: Adaptive LLM Routing with Test-Time Optimal Compute","created":"2025-06-28","cited_by_count":67},{"id":"2505.14631","title":"Think Only When You Need with Large Hybrid-Reasoning Models","created":"2025-05-20","cited_by_count":66},{"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":"2408.13457","title":"Make Every Penny Count: Difficulty-Adaptive Self-Consistency for Cost-Efficient Reasoning","created":"2024-08-24","cited_by_count":63},{"id":"2408.17017","title":"Reasoning Aware Self-Consistency: Leveraging Reasoning Paths for Efficient LLM Sampling","created":"2024-08-30","cited_by_count":63},{"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":"1810.13306","title":"Automated Machine Learning: From Principles to Practices","created":"2018-10-31","cited_by_count":62},{"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":"2503.10657","title":"RouterEval: A Comprehensive Benchmark for Routing LLMs to Explore Model-level Scaling Up in LLMs","created":"2025-03-08","cited_by_count":61},{"id":"2503.23077","title":"Efficient Inference for Large Reasoning Models: A Survey","created":"2025-03-29","cited_by_count":61},{"id":"2411.01855","title":"Can Language Models Learn to Skip Steps?","created":"2024-11-04","cited_by_count":59},{"id":"2504.07891","title":"SpecReason: Fast and Accurate Inference-Time Compute via Speculative Reasoning","created":"2025-04-10","cited_by_count":59},{"id":"2412.20993","title":"Efficiently Scaling LLM Reasoning with Certaindex","created":"2024-12-30","cited_by_count":58},{"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},{"id":"2506.05256","title":"Just Enough Thinking: Efficient Reasoning with Adaptive Length Penalties Reinforcement Learning","created":"2025-06-05","cited_by_count":52},{"id":"2506.02867","title":"Demystifying Reasoning Dynamics with Mutual Information: Thinking Tokens are Information Peaks in LLM Reasoning","created":"2025-06-03","cited_by_count":51},{"id":"2505.18227","title":"Token Reduction Should Go Beyond Efficiency in Generative Models -- From Vision, Language to Multimodality","created":"2025-05-23","cited_by_count":50},{"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":"2505.11274","title":"SelfBudgeter: Adaptive Token Allocation for Efficient LLM Reasoning","created":"2025-05-16","cited_by_count":48},{"id":"2407.02511","title":"LLM-A*: Large Language Model Enhanced Incremental Heuristic Search on Path Planning","created":"2024-06-20","cited_by_count":45},{"id":"2504.13171","title":"Sleep-time Compute: Beyond Inference Scaling at Test-time","created":"2025-04-17","cited_by_count":43},{"id":"2502.16235","title":"Dynamic Parallel Tree Search for Efficient LLM Reasoning","created":"2025-02-22","cited_by_count":42},{"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":"2506.14755","title":"Optimizing Length Compression in Large Reasoning Models","created":"2025-06-17","cited_by_count":38},{"id":"2508.03346","title":"Making Slow Thinking Faster: Compressing LLM Chain-of-Thought via Step Entropy","created":"2025-08-05","cited_by_count":38},{"id":"2510.26768","title":"AMO-Bench: Large Language Models Still Struggle in High School Math Competitions","created":"2025-10-30","cited_by_count":38},{"id":"2504.00810","title":"Z1: Efficient Test-time Scaling with Code","created":"2025-04-01","cited_by_count":35},{"id":"2504.13367","title":"THOUGHTTERMINATOR: Benchmarking, Calibrating, and Mitigating Overthinking in Reasoning Models","created":"2025-04-17","cited_by_count":35},{"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":"2508.13141","title":"OptimalThinkingBench: Evaluating Over and Underthinking in LLMs","created":"2025-08-18","cited_by_count":35}],"next_cursor":"100"}