{"list":"other","total":52,"rows":[{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2402.03300","title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","created":"2024-02-05","cited_by_count":9379},{"id":"2501.12948","title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","created":"2025-01-22","cited_by_count":6330},{"id":"2203.11171","title":"Self-Consistency Improves Chain of Thought Reasoning in Language Models","created":"2022-03-21","cited_by_count":5708},{"id":"1809.09600","title":"HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering","created":"2018-09-25","cited_by_count":3754},{"id":"2205.14135","title":"FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness","created":"2022-05-27","cited_by_count":3673},{"id":"2307.08691","title":"FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning","created":"2023-07-17","cited_by_count":2598},{"id":"2211.17192","title":"Fast Inference from Transformers via Speculative Decoding","created":"2022-11-30","cited_by_count":1653},{"id":"2305.15334","title":"Gorilla: Large Language Model Connected with Massive APIs","created":"2023-05-24","cited_by_count":1332},{"id":"1909.06146","title":"PubMedQA: A Dataset for Biomedical Research Question Answering","created":"2019-09-13","cited_by_count":1288},{"id":"2007.01282","title":"Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering","created":"2020-07-02","cited_by_count":1210},{"id":"2302.01318","title":"Accelerating Large Language Model Decoding with Speculative Sampling","created":"2023-02-02","cited_by_count":1006},{"id":"2404.14469","title":"SnapKV: LLM Knows What You are Looking for Before Generation","created":"2024-04-22","cited_by_count":880},{"id":"2401.18079","title":"KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization","created":"2024-01-31","cited_by_count":591},{"id":"2406.04692","title":"Mixture-of-Agents Enhances Large Language Model Capabilities","created":"2024-06-07","cited_by_count":438},{"id":"2502.05171","title":"Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach","created":"2025-02-07","cited_by_count":415},{"id":"2402.02057","title":"Break the Sequential Dependency of LLM Inference Using Lookahead Decoding","created":"2024-02-03","cited_by_count":298},{"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":"2410.10819","title":"DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads","created":"2024-10-14","cited_by_count":288},{"id":"2403.10131","title":"RAFT: Adapting Language Model to Domain Specific RAG","created":"2024-03-15","cited_by_count":262},{"id":"2405.00451","title":"Monte Carlo Tree Search Boosts Reasoning via Iterative Preference Learning","created":"2024-05-01","cited_by_count":241},{"id":"2407.11550","title":"Ada-KV: Optimizing KV Cache Eviction by Adaptive Budget Allocation for Efficient LLM Inference","created":"2024-07-16","cited_by_count":235},{"id":"2402.10200","title":"Chain-of-Thought Reasoning Without Prompting","created":"2024-02-15","cited_by_count":210},{"id":"2406.07394","title":"Accessing GPT-4 level Mathematical Olympiad Solutions via Monte Carlo Tree Self-refine with LLaMa-3 8B","created":"2024-06-11","cited_by_count":158},{"id":"2411.14405","title":"Marco-o1: Towards Open Reasoning Models for Open-Ended Solutions","created":"2024-11-21","cited_by_count":144},{"id":"2408.06195","title":"Mutual Reasoning Makes Smaller LLMs Stronger Problem-Solvers","created":"2024-08-12","cited_by_count":138},{"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":"2310.07177","title":"Online Speculative Decoding","created":"2023-10-11","cited_by_count":113},{"id":"2406.11430","title":"A Simple and Effective $L_2$ Norm-Based Strategy for KV Cache Compression","created":"2024-06-17","cited_by_count":86},{"id":"2409.03733","title":"Planning In Natural Language Improves LLM Search For Code Generation","created":"2024-09-05","cited_by_count":83},{"id":"2407.08223","title":"Speculative RAG: Enhancing Retrieval Augmented Generation through Drafting","created":"2024-07-11","cited_by_count":77},{"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":"2407.21018","title":"ThinK: Thinner Key Cache by Query-Driven Pruning","created":"2024-07-30","cited_by_count":68},{"id":"2502.16002","title":"KVLink: Accelerating Large Language Models via Efficient KV Cache Reuse","created":"2025-02-21","cited_by_count":66},{"id":"2410.01707","title":"Interpretable Contrastive Monte Carlo Tree Search Reasoning","created":"2024-10-02","cited_by_count":64},{"id":"2411.11694","title":"Enhancing LLM Reasoning with Reward-guided Tree Search","created":"2024-11-18","cited_by_count":58},{"id":"2501.19306","title":"SETS: Leveraging Self-Verification and Self-Correction for Improved Test-Time Scaling","created":"2025-01-31","cited_by_count":54},{"id":"2501.14342","title":"Chain-of-Retrieval Augmented Generation","created":"2025-01-24","cited_by_count":49},{"id":"2403.14541","title":"EDT: Improving Large Language Models' Generation by Entropy-based Dynamic Temperature Sampling","created":"2024-03-21","cited_by_count":45},{"id":"2501.02497","title":"A Survey of Test-Time Compute: From Intuitive Inference to Deliberate Reasoning","created":"2025-01-05","cited_by_count":40},{"id":"2501.15915","title":"Parametric Retrieval Augmented Generation","created":"2025-01-27","cited_by_count":38},{"id":"2402.01528","title":"Decoding Speculative Decoding","created":"2024-02-02","cited_by_count":34},{"id":"2502.07202","title":"Monte Carlo Tree Diffusion for System 2 Planning","created":"2025-02-11","cited_by_count":33},{"id":"2502.02339","title":"AStar: Boosting Multimodal Reasoning with Automated Structured Thinking","created":"2025-02-04","cited_by_count":25},{"id":"2502.02584","title":"QLASS: Boosting Language Agent Inference via Q-Guided Stepwise Search","created":"2025-02-04","cited_by_count":20},{"id":"2502.12130","title":"Scaling Autonomous Agents via Automatic Reward Modeling And Planning","created":"2025-02-17","cited_by_count":19},{"id":"2406.12050","title":"Learn Beyond The Answer: Training Language Models with Reflection for Mathematical Reasoning","created":"2024-06-17","cited_by_count":15},{"id":"2503.21720","title":"Collab: Controlled Decoding using Mixture of Agents for LLM Alignment","created":"2025-03-27","cited_by_count":14},{"id":"2502.04728","title":"Generating Symbolic World Models via Test-time Scaling of Large Language Models","created":"2025-02-07","cited_by_count":12},{"id":"2410.20215","title":"DAWN-ICL: Strategic Planning of Problem-solving Trajectories for Zero-Shot In-Context Learning","created":"2024-10-26","cited_by_count":6},{"id":"2502.06833","title":"Entropy Adaptive Decoding: Dynamic Model Switching for Efficient Inference","created":"2025-02-05","cited_by_count":5},{"id":"2404.09338","title":"Entropy Guided Extrapolative Decoding to Improve Factuality in Large Language Models","created":"2024-04-14","cited_by_count":4}],"next_cursor":null}