{"total":118,"rows":[{"id":"2412.19437","title":"DeepSeek-V3 Technical Report","created":"2024-12-27","cited_by_count":811,"area":"lr"},{"id":"2507.02259","title":"MemAgent: Reshaping Long-Context LLM with Multi-Conv RL-based Memory Agent","created":"2025-07-03","cited_by_count":246,"area":"lr"},{"id":"2504.02495","title":"Inference-Time Scaling for Generalist Reward Modeling","created":"2025-04-03","cited_by_count":239,"area":"lr"},{"id":"2502.21321","title":"LLM Post-Training: A Deep Dive into Reasoning Large Language Models","created":"2025-02-28","cited_by_count":135,"area":"lr"},{"id":"2412.19442","title":"A Survey on Large Language Model Acceleration based on KV Cache Management","created":"2024-12-27","cited_by_count":131,"area":"lr"},{"id":"2501.01257","title":"CodeElo: Benchmarking Competition-level Code Generation of LLMs with Human-comparable Elo Ratings","created":"2025-01-02","cited_by_count":115,"area":"lr"},{"id":"2505.12346","title":"SEED-GRPO: Semantic Entropy Enhanced GRPO for Uncertainty-Aware Policy Optimization","created":"2025-05-18","cited_by_count":89,"area":"lr"},{"id":"2501.11425","title":"Agent-R: Training Language Model Agents to Reflect via Iterative Self-Training","created":"2025-01-20","cited_by_count":82,"area":"lr"},{"id":"2504.02259","title":"T*: Re-thinking Temporal Search for Long-Form Video Understanding","created":"2025-04-03","cited_by_count":82,"area":"lr"},{"id":"2412.10400","title":"Reinforcement Learning Enhanced LLMs: A Survey","created":"2024-12-05","cited_by_count":71,"area":"lr"},{"id":"2503.07065","title":"Boosting the Generalization and Reasoning of Vision Language Models with Curriculum Reinforcement Learning","created":"2025-03-10","cited_by_count":71,"area":"lr"},{"id":"2407.09887","title":"OptiBench Meets ReSocratic: Measure and Improve LLMs for Optimization Modeling","created":"2024-07-13","cited_by_count":68,"area":"lr"},{"id":"2408.16737","title":"Smaller, Weaker, Yet Better: Training LLM Reasoners via Compute-Optimal Sampling","created":"2024-08-29","cited_by_count":61,"area":"lr"},{"id":"2502.07316","title":"CodeI/O: Condensing Reasoning Patterns via Code Input-Output Prediction","created":"2025-02-11","cited_by_count":55,"area":"lr"},{"id":"2405.13144","title":"LLMs for Mathematical Modeling: Towards Bridging the Gap between Natural and Mathematical Languages","created":"2024-05-21","cited_by_count":49,"area":"lr"},{"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,"area":"lr"},{"id":"2410.09008","title":"SuperCorrect: Advancing Small LLM Reasoning with Thought Template Distillation and Self-Correction","created":"2024-10-11","cited_by_count":40,"area":"lr"},{"id":"2506.04301","title":"The Cost of Dynamic Reasoning: Demystifying AI Agents and Test-Time Scaling from an AI Infrastructure Perspective","created":"2025-06-04","cited_by_count":39,"area":"lr"},{"id":"2505.12415","title":"Table-R1: Region-based Reinforcement Learning for Table Understanding","created":"2025-05-18","cited_by_count":37,"area":"lr"},{"id":"2505.02018","title":"R-Bench: Graduate-level Multi-disciplinary Benchmarks for LLM & MLLM Complex Reasoning Evaluation","created":"2025-05-04","cited_by_count":34,"area":"lr"},{"id":"2502.20808","title":"MV-MATH: Evaluating Multimodal Math Reasoning in Multi-Visual Contexts","created":"2025-02-28","cited_by_count":32,"area":"lr"},{"id":"2406.13948","title":"CityGPT: Empowering Urban Spatial Cognition of Large Language Models","created":"2024-06-20","cited_by_count":30,"area":"lr"},{"id":"2409.18938","title":"From Seconds to Hours: Reviewing MultiModal Large Language Models on Comprehensive Long Video Understanding","created":"2024-09-27","cited_by_count":30,"area":"lr"},{"id":"2506.08889","title":"SeerAttention-R: Sparse Attention Adaptation for Long Reasoning","created":"2025-06-10","cited_by_count":30,"area":"lr"},{"id":"2408.16326","title":"Critic-CoT: Boosting the reasoning abilities of large language model via Chain-of-thoughts Critic","created":"2024-08-29","cited_by_count":28,"area":"lr"},{"id":"2412.17596","title":"Evaluating LLMs' Divergent Thinking Capabilities for Scientific Idea Generation with Minimal Context","created":"2024-12-23","cited_by_count":28,"area":"lr"},{"id":"2506.05345","title":"Inference-Time Hyper-Scaling with KV Cache Compression","created":"2025-06-05","cited_by_count":27,"area":"lr"},{"id":"2510.01499","title":"Beyond Majority Voting: LLM Aggregation by Leveraging Higher-Order Information","created":"2025-10-01","cited_by_count":26,"area":"lr"},{"id":"2409.15156","title":"Rethinking Conventional Wisdom in Machine Learning: From Generalization to Scaling","created":"2024-09-23","cited_by_count":23,"area":"lr"},{"id":"2505.18610","title":"PM-KVQ: Progressive Mixed-precision KV Cache Quantization for Long-CoT LLMs","created":"2025-05-24","cited_by_count":22,"area":"lr"},{"id":"2507.04136","title":"A Technical Survey of Reinforcement Learning Techniques for Large Language Models","created":"2025-07-05","cited_by_count":21,"area":"lr"},{"id":"2502.13834","title":"Proving Olympiad Inequalities by Synergizing LLMs and Symbolic Reasoning","created":"2025-02-19","cited_by_count":17,"area":"lr"},{"id":"2502.01941","title":"Semantic Integrity Matters: Benchmarking and Preserving High-Density Reasoning in KV Cache Compression","created":"2025-02-04","cited_by_count":16,"area":"lr"},{"id":"2503.04779","title":"Can LLMs Reason About Program Semantics? A Comprehensive Evaluation of LLMs on Formal Specification Inference","created":"2025-02-22","cited_by_count":16,"area":"lr"},{"id":"2505.07889","title":"BioProBench: A Corpus and Benchmark for Biological Protocol Reasoning in Autonomous Science","created":"2025-05-11","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":"2409.12929","title":"LogicPro: Improving Complex Logical Reasoning via Program-Guided Learning","created":"2024-09-19","cited_by_count":14,"area":"lr"},{"id":"2501.13766","title":"UGMathBench: A Diverse and Dynamic Benchmark for Undergraduate-Level Mathematical Reasoning with Large Language Models","created":"2025-01-23","cited_by_count":13,"area":"lr"},{"id":"2501.05727","title":"Self-Evolving Critique Abilities in Large Language Models","created":"2025-01-10","cited_by_count":12,"area":"lr"},{"id":"2506.05333","title":"Kinetics: Rethinking Test-Time Scaling Laws","created":"2025-06-05","cited_by_count":12,"area":"lr"},{"id":"2507.08297","title":"KAT-V1: Kwai-AutoThink Technical Report","created":"2025-07-11","cited_by_count":12,"area":"lr"},{"id":"2507.15849","title":"The Impact of Language Mixing on Bilingual LLM Reasoning","created":"2025-07-21","cited_by_count":12,"area":"lr"},{"id":"2508.15861","title":"XFinBench: Benchmarking LLMs in Complex Financial Problem Solving and Reasoning","created":"2025-08-20","cited_by_count":12,"area":"lr"},{"id":"2509.17677","title":"EngiBench: A Benchmark for Evaluating Large Language Models on Engineering Problem Solving","created":"2025-09-22","cited_by_count":12,"area":"lr"},{"id":"2603.28743","title":"Rethinking Language Model Scaling under Transferable Hypersphere Optimization","created":"2026-03-30","cited_by_count":12,"area":"lr"},{"id":"2507.06607","title":"Decoder-Hybrid-Decoder Architecture for Efficient Reasoning with Long Generation","created":"2025-07-09","cited_by_count":11,"area":"lr"},{"id":"2508.00579","title":"MHier-RAG: Multi-Modal RAG for Visual-Rich Document Question-Answering via Hierarchical and Multi-Granularity Reasoning","created":"2025-08-01","cited_by_count":11,"area":"lr"},{"id":"2510.01270","title":"Think Twice, Generate Once: Safeguarding by Progressive Self-Reflection","created":"2025-09-29","cited_by_count":11,"area":"lr"},{"id":"2602.22603","title":"SideQuest: Model-Driven KV Cache Management for Long-Horizon Agentic Reasoning","created":"2026-02-26","cited_by_count":11,"area":"lr"},{"id":"2409.11056","title":"Large Language Models are Good Multi-lingual Learners : When LLMs Meet Cross-lingual Prompts","created":"2024-09-17","cited_by_count":10,"area":"lr"},{"id":"2412.08054","title":"Federated In-Context LLM Agent Learning","created":"2024-12-11","cited_by_count":10,"area":"lr"},{"id":"2509.24193","title":"AceSearcher: Bootstrapping Reasoning and Search for LLMs via Reinforced Self-Play","created":"2025-09-29","cited_by_count":10,"area":"lr"},{"id":"2510.08525","title":"Which Heads Matter for Reasoning? RL-Guided KV Cache Compression","created":"2025-10-09","cited_by_count":10,"area":"lr"},{"id":"2511.23478","title":"Video-R2: Reinforcing Consistent and Grounded Reasoning in Multimodal Language Models","created":"2025-11-28","cited_by_count":10,"area":"lr"},{"id":"2410.17558","title":"CLR-Bench: Evaluating Large Language Models in College-level Reasoning","created":"2024-10-23","cited_by_count":9,"area":"lr"},{"id":"2502.11169","title":"CMCTS: A Constrained Monte Carlo Tree Search Framework for Mathematical Reasoning in Large Language Model","created":"2025-02-16","cited_by_count":9,"area":"lr"},{"id":"2510.12680","title":"Demystifying Hybrid Thinking: Can LLMs Truly Switch Between Think and No-Think?","created":"2025-10-14","cited_by_count":9,"area":"lr"},{"id":"2503.01539","title":"Pragmatic Inference Chain (PIC) Improving LLMs' Reasoning of Authentic Implicit Toxic Language","created":"2025-03-03","cited_by_count":8,"area":"lr"},{"id":"2503.10573","title":"Evaluating Mathematical Reasoning Across Large Language Models: A Fine-Grained Approach","created":"2025-03-13","cited_by_count":8,"area":"lr"},{"id":"2606.03928","title":"Value-Aware Stochastic KV Cache Eviction for Reasoning Models","created":"2026-06-02","cited_by_count":8,"area":"lr"},{"id":"2408.11326","title":"Automating Thought of Search: A Journey Towards Soundness and Completeness","created":"2024-08-21","cited_by_count":7,"area":"lr"},{"id":"2410.01504","title":"PersonaMath: Boosting Mathematical Reasoning via Persona-Driven Data Augmentation","created":"2024-10-02","cited_by_count":7,"area":"lr"},{"id":"2501.11790","title":"Benchmarking LLMs' Mathematical Reasoning with Unseen Random Variables Questions","created":"2025-01-20","cited_by_count":7,"area":"lr"},{"id":"2509.22824","title":"Critique-Coder: Enhancing Coder Models by Critique Reinforcement Learning","created":"2025-09-26","cited_by_count":7,"area":"lr"},{"id":"2604.24432","title":"Kwai Summary Attention Technical Report","created":"2026-04-27","cited_by_count":7,"area":"lr"},{"id":"2502.17947","title":"DeepSeek-R1 Outperforms Gemini 2.0 Pro, OpenAI o1, and o3-mini in Bilingual Complex Ophthalmology Reasoning","created":"2025-02-25","cited_by_count":6,"area":"lr"},{"id":"2512.00305","title":"ChartPoint: Guiding MLLMs with Grounding Reflection for Chart Reasoning","created":"2025-11-29","cited_by_count":6,"area":"lr"},{"id":"2601.07036","title":"Mid-Think: Training-Free Intermediate-Budget Reasoning via Token-Level Triggers","created":"2026-01-11","cited_by_count":6,"area":"lr"},{"id":"2606.03458","title":"KVarN: Variance-Normalized KV-Cache Quantization Mitigates Error Accumulation in Reasoning Tasks","created":"2026-06-02","cited_by_count":6,"area":"lr"},{"id":"2606.18967","title":"EfficientRollout: System-Aware Self-Speculative Decoding for RL Rollouts","created":"2026-06-17","cited_by_count":6,"area":"lr"},{"id":"2506.01969","title":"FlashMLA-ETAP: Efficient Transpose Attention Pipeline for Accelerating MLA Inference on NVIDIA H20 GPUs","created":"2025-05-13","cited_by_count":5,"area":"lr"},{"id":"2506.18781","title":"Existing LLMs Are Not Self-Consistent For Simple Tasks","created":"2025-06-23","cited_by_count":5,"area":"lr"},{"id":"2507.00004","title":"A Theory of Inference Compute Scaling: Reasoning through Directed Stochastic Skill Search","created":"2025-06-10","cited_by_count":5,"area":"lr"},{"id":"2511.06029","title":"Lethe: Layer- and Time-Adaptive KV Cache Pruning for Reasoning-Intensive LLM Serving","created":"2025-11-08","cited_by_count":5,"area":"lr"},{"id":"2602.01365","title":"When Domains Interact: Asymmetric and Order-Sensitive Cross-Domain Effects in Reinforcement Learning for Reasoning","created":"2026-02-01","cited_by_count":5,"area":"lr"},{"id":"2603.12698","title":"EvolveCoder: Evolving Test Cases via Adversarial Verification for Code Reinforcement Learning","created":"2026-03-13","cited_by_count":5,"area":"lr"},{"id":"2507.22003","title":"See Different, Think Better: Visual Variations Mitigating Hallucinations in LVLMs","created":"2025-07-29","cited_by_count":4,"area":"lr"},{"id":"2510.07169","title":"More Data or Better Data? A Critical Analysis of Data Selection and Synthesis for Mathematical Reasoning","created":"2025-10-08","cited_by_count":4,"area":"lr"},{"id":"2512.23213","title":"Scoring, Reasoning, and Selecting the Best! Ensembling Large Language Models via a Peer-Review Process","created":"2025-12-29","cited_by_count":4,"area":"lr"},{"id":"2603.24984","title":"MoE-GRPO: Optimizing Mixture-of-Experts via Reinforcement Learning in Vision-Language Models","created":"2026-03-26","cited_by_count":4,"area":"lr"},{"id":"2410.04422","title":"Long-context Language Models Fail in Basic Retrieval Tasks Without Sufficient Reasoning Steps","created":"2024-10-06","cited_by_count":3,"area":"lr"},{"id":"2501.11599","title":"SR-FoT: A Syllogistic-Reasoning Framework of Thought for Large Language Models Tackling Knowledge-based Reasoning Tasks","created":"2025-01-20","cited_by_count":3,"area":"lr"},{"id":"2503.03645","title":"Psy-Copilot: Visual Chain of Thought for Counseling","created":"2025-03-05","cited_by_count":3,"area":"lr"},{"id":"2503.11486","title":"A Review of DeepSeek Models' Key Innovative Techniques","created":"2025-03-14","cited_by_count":3,"area":"lr"},{"id":"2505.18831","title":"Enhancing LLMs' Reasoning-Intensive Multimedia Search Capabilities through Fine-Tuning and Reinforcement Learning","created":"2025-05-24","cited_by_count":3,"area":"lr"},{"id":"2506.08352","title":"Reinforcement Fine-Tuning for Reasoning towards Multi-Step Multi-Source Search in Large Language Models","created":"2025-06-10","cited_by_count":3,"area":"lr"},{"id":"2508.11196","title":"UAV-VL-R1: Generalizing Vision-Language Models via Supervised Fine-Tuning and Multi-Stage GRPO for UAV Visual Reasoning","created":"2025-08-15","cited_by_count":3,"area":"lr"},{"id":"2512.06201","title":"K2-V2: A 360-Open, Reasoning-Enhanced LLM","created":"2025-12-05","cited_by_count":3,"area":"lr"},{"id":"2604.27201","title":"Path-Lock Expert: Separating Reasoning Mode in Hybrid Thinking via Architecture-Level Separation","created":"2026-04-29","cited_by_count":3,"area":"lr"},{"id":"2605.08876","title":"OTora: A Unified Red Teaming Framework for Reasoning-Level Denial-of-Service in LLM Agents","created":"2026-05-09","cited_by_count":3,"area":"lr"},{"id":"2502.11573","title":"InfiR : Crafting Effective Small Language Models and Multimodal Small Language Models in Reasoning","created":"2025-02-17","cited_by_count":2,"area":"lr"},{"id":"2502.11901","title":"Building A Proof-Oriented Programmer That Is 64% Better Than GPT-4o Under Data Scarcity","created":"2025-02-17","cited_by_count":2,"area":"lr"},{"id":"2502.21309","title":"Reasoning is Periodicity? Improving Large Language Models Through Effective Periodicity Modeling","created":"2025-02-28","cited_by_count":2,"area":"lr"},{"id":"2505.19112","title":"Self-Critique Guided Iterative Reasoning for Multi-hop Question Answering","created":"2025-05-25","cited_by_count":2,"area":"lr"},{"id":"2505.19621","title":"Think Again! The Effect of Test-Time Compute on Preferences, Opinions, and Beliefs of Large Language Models","created":"2025-05-26","cited_by_count":2,"area":"lr"},{"id":"2508.16514","title":"FLAMES: Improving LLM Math Reasoning via a Fine-Grained Analysis of the Data Synthesis Pipeline","created":"2025-08-22","cited_by_count":2,"area":"lr"},{"id":"2509.12645","title":"Large Language Models Imitate Logical Reasoning, but at what Cost?","created":"2025-09-16","cited_by_count":2,"area":"lr"},{"id":"2509.23686","title":"Evaluating Program Semantics Reasoning with Type Inference in System F","created":"2025-09-28","cited_by_count":2,"area":"lr"},{"id":"2510.07486","title":"AsyncSpade: Efficient Test-Time Scaling with Asynchronous Sparse Decoding","created":"2025-10-08","cited_by_count":2,"area":"lr"},{"id":"2511.02651","title":"Apriel-H1: Towards Efficient Enterprise Reasoning Models","created":"2025-11-04","cited_by_count":2,"area":"lr"}],"next_cursor":"100"}