{"total":173,"rows":[{"id":"2308.09583","title":"WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-Instruct","created":"2023-08-18","cited_by_count":625,"area":"lr"},{"id":"2403.17887","title":"The Unreasonable Ineffectiveness of the Deeper Layers","created":"2024-03-26","cited_by_count":226,"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":"2402.05602","title":"AttnLRP: Attention-Aware Layer-Wise Relevance Propagation for Transformers","created":"2024-02-08","cited_by_count":120,"area":"lr"},{"id":"2502.15589","title":"LightThinker: Thinking Step-by-Step Compression","created":"2025-02-21","cited_by_count":104,"area":"lr"},{"id":"2310.20689","title":"Learning From Mistakes Makes LLM Better Reasoner","created":"2023-10-31","cited_by_count":101,"area":"lr"},{"id":"2506.24119","title":"SPIRAL: Self-Play on Zero-Sum Games Incentivizes Reasoning via Multi-Agent Multi-Turn Reinforcement Learning","created":"2025-06-30","cited_by_count":100,"area":"lr"},{"id":"2502.18439","title":"MAPoRL: Multi-Agent Post-Co-Training for Collaborative Large Language Models with Reinforcement Learning","created":"2025-02-25","cited_by_count":86,"area":"lr"},{"id":"2405.10825","title":"Large Language Model (LLM) for Telecommunications: A Comprehensive Survey on Principles, Key Techniques, and Opportunities","created":"2024-05-17","cited_by_count":83,"area":"lr"},{"id":"2311.09827","title":"Cognitive Overload: Jailbreaking Large Language Models with Overloaded Logical Thinking","created":"2023-11-16","cited_by_count":81,"area":"lr"},{"id":"2310.08034","title":"Receive, Reason, and React: Drive as You Say with Large Language Models in Autonomous Vehicles","created":"2023-10-12","cited_by_count":72,"area":"lr"},{"id":"2412.10400","title":"Reinforcement Learning Enhanced LLMs: A Survey","created":"2024-12-05","cited_by_count":71,"area":"lr"},{"id":"2407.21018","title":"ThinK: Thinner Key Cache by Query-Driven Pruning","created":"2024-07-30","cited_by_count":68,"area":"lr"},{"id":"2310.16755","title":"HI-TOM: A Benchmark for Evaluating Higher-Order Theory of Mind Reasoning in Large Language Models","created":"2023-10-25","cited_by_count":63,"area":"lr"},{"id":"2312.17080","title":"MR-GSM8K: A Meta-Reasoning Benchmark for Large Language Model Evaluation","created":"2023-12-28","cited_by_count":57,"area":"lr"},{"id":"2404.04925","title":"Multilingual Large Language Model: A Survey of Resources, Taxonomy and Frontiers","created":"2024-04-07","cited_by_count":51,"area":"lr"},{"id":"2406.15992","title":"Can LLM Graph Reasoning Generalize beyond Pattern Memorization?","created":"2024-06-23","cited_by_count":47,"area":"lr"},{"id":"2408.15769","title":"A Survey on Evaluation of Multimodal Large Language Models","created":"2024-08-28","cited_by_count":46,"area":"lr"},{"id":"2410.05669","title":"ACPBench: Reasoning about Action, Change, and Planning","created":"2024-10-08","cited_by_count":39,"area":"lr"},{"id":"2411.15382","title":"On the Impact of Fine-Tuning on Chain-of-Thought Reasoning","created":"2024-11-22","cited_by_count":32,"area":"lr"},{"id":"2402.11442","title":"Can LLMs Reason with Rules? Logic Scaffolding for Stress-Testing and Improving LLMs","created":"2024-02-18","cited_by_count":28,"area":"lr"},{"id":"2310.11716","title":"Reflection-Tuning: Data Recycling Improves LLM Instruction-Tuning","created":"2023-10-18","cited_by_count":26,"area":"lr"},{"id":"2412.00383","title":"Unified Parameter-Efficient Unlearning for LLMs","created":"2024-11-30","cited_by_count":25,"area":"lr"},{"id":"2405.00402","title":"Self-Refine Instruction-Tuning for Aligning Reasoning in Language Models","created":"2024-05-01","cited_by_count":24,"area":"lr"},{"id":"2506.08295","title":"From Passive to Active Reasoning: Can Large Language Models Ask the Right Questions under Incomplete Information?","created":"2025-06-09","cited_by_count":23,"area":"lr"},{"id":"2311.09241","title":"Chain of Images for Intuitively Reasoning","created":"2023-11-09","cited_by_count":21,"area":"lr"},{"id":"2311.10797","title":"TaCo: Enhancing Cross-Lingual Transfer for Low-Resource Languages in LLMs through Translation-Assisted Chain-of-Thought Processes","created":"2023-11-17","cited_by_count":19,"area":"lr"},{"id":"2312.10730","title":"Mixed Distillation Helps Smaller Language Model Better Reasoning","created":"2023-12-17","cited_by_count":19,"area":"lr"},{"id":"2401.13223","title":"TAT-LLM: A Specialized Language Model for Discrete Reasoning over Tabular and Textual Data","created":"2024-01-24","cited_by_count":19,"area":"lr"},{"id":"2405.00622","title":"Causal Evaluation of Language Models","created":"2024-05-01","cited_by_count":18,"area":"lr"},{"id":"2502.15799","title":"Investigating the Impact of Quantization Methods on the Safety and Reliability of Large Language Models","created":"2025-02-18","cited_by_count":18,"area":"lr"},{"id":"2505.06413","title":"Natural Reflection Backdoor Attack on Vision Language Model for Autonomous Driving","created":"2025-05-09","cited_by_count":18,"area":"lr"},{"id":"2408.03533","title":"Lifelong Personalized Low-Rank Adaptation of Large Language Models for Recommendation","created":"2024-08-07","cited_by_count":17,"area":"lr"},{"id":"2404.08382","title":"Look at the Text: Instruction-Tuned Language Models are More Robust Multiple Choice Selectors than You Think","created":"2024-04-12","cited_by_count":14,"area":"lr"},{"id":"2506.01748","title":"Thinking in Character: Advancing Role-Playing Agents with Role-Aware Reasoning","created":"2025-06-02","cited_by_count":14,"area":"lr"},{"id":"2602.04118","title":"Learning to Reason in 13 Parameters","created":"2026-02-04","cited_by_count":14,"area":"lr"},{"id":"2402.16631","title":"GenAINet: Enabling Wireless Collective Intelligence via Knowledge Transfer and Reasoning","created":"2024-02-26","cited_by_count":13,"area":"lr"},{"id":"2404.04627","title":"Self-Training Large Language Models for Improved Visual Program Synthesis With Visual Reinforcement","created":"2024-04-06","cited_by_count":12,"area":"lr"},{"id":"2510.25588","title":"Standardization of Psychiatric Diagnoses -- Role of Fine-tuned LLM Consortium and OpenAI-gpt-oss Reasoning LLM Enabled Decision Support System","created":"2025-10-29","cited_by_count":12,"area":"lr"},{"id":"2310.13855","title":"Evoke: Evoking Critical Thinking Abilities in LLMs via Reviewer-Author Prompt Editing","created":"2023-10-20","cited_by_count":11,"area":"lr"},{"id":"2312.16279","title":"Cloud-Device Collaborative Learning for Multimodal Large Language Models","created":"2023-12-26","cited_by_count":11,"area":"lr"},{"id":"2402.03877","title":"Beyond Lines and Circles: Unveiling the Geometric Reasoning Gap in Large Language Models","created":"2024-02-06","cited_by_count":11,"area":"lr"},{"id":"2504.18671","title":"Proof-of-TBI -- Fine-Tuned Vision Language Model Consortium and OpenAI-o3 Reasoning LLM-Based Medical Diagnosis Support System for Mild Traumatic Brain Injury (TBI) Prediction","created":"2025-04-25","cited_by_count":11,"area":"lr"},{"id":"2508.16695","title":"Do Cognitively Interpretable Reasoning Traces Improve LLM Performance?","created":"2025-08-21","cited_by_count":11,"area":"lr"},{"id":"2509.23324","title":"Scaling LLM Test-Time Compute with Mobile NPU on Smartphones","created":"2025-09-27","cited_by_count":11,"area":"lr"},{"id":"2506.05745","title":"SPRINT: Enabling Interleaved Planning and Parallelized Execution in Reasoning Models","created":"2025-06-06","cited_by_count":10,"area":"lr"},{"id":"2603.24840","title":"Prune as You Generate: Online Rollout Pruning for Faster and Better RLVR","created":"2026-03-25","cited_by_count":10,"area":"lr"},{"id":"2404.02934","title":"GreedLlama: Performance of Financial Value-Aligned Large Language Models in Moral Reasoning","created":"2024-04-03","cited_by_count":9,"area":"lr"},{"id":"2504.15241","title":"MrGuard: A Multilingual Reasoning Guardrail for Universal LLM Safety","created":"2025-04-21","cited_by_count":9,"area":"lr"},{"id":"2512.11847","title":"Tiny Recursive Models on ARC-AGI-1: Inductive Biases, Identity Conditioning, and Test-Time Compute","created":"2025-12-04","cited_by_count":9,"area":"lr"},{"id":"2407.11638","title":"A Comprehensive Evaluation of Large Language Models on Temporal Event Forecasting","created":"2024-07-16","cited_by_count":8,"area":"lr"},{"id":"2412.00151","title":"DLaVA: Document Language and Vision Assistant for Answer Localization with Enhanced Interpretability and Trustworthiness","created":"2024-11-29","cited_by_count":8,"area":"lr"},{"id":"2503.06518","title":"Towards Superior Quantization Accuracy: A Layer-sensitive Approach","created":"2025-03-09","cited_by_count":8,"area":"lr"},{"id":"2505.13792","title":"Interpretable Traces, Unexpected Outcomes: Investigating the Disconnect in Trace-Based Knowledge Distillation","created":"2025-05-20","cited_by_count":8,"area":"lr"},{"id":"2601.14290","title":"Project Aletheia: Verifier-Guided Distillation of Backtracking for Small Language Models","created":"2026-01-14","cited_by_count":8,"area":"lr"},{"id":"2602.13953","title":"QuRL: Efficient Reinforcement Learning with Quantized Rollout","created":"2026-02-15","cited_by_count":8,"area":"lr"},{"id":"2402.10744","title":"GenRES: Rethinking Evaluation for Generative Relation Extraction in the Era of Large Language Models","created":"2024-02-16","cited_by_count":7,"area":"lr"},{"id":"2404.09077","title":"CuriousLLM: Elevating Multi-Document Question Answering with LLM-Enhanced Knowledge Graph Reasoning","created":"2024-04-13","cited_by_count":7,"area":"lr"},{"id":"2504.08690","title":"Fast-Slow-Thinking: Complex Task Solving with Large Language Models","created":"2025-04-11","cited_by_count":7,"area":"lr"},{"id":"2505.07861","title":"Scalable LLM Reasoning Acceleration with Low-rank Distillation","created":"2025-05-08","cited_by_count":7,"area":"lr"},{"id":"2506.03700","title":"AdaDecode: Accelerating LLM Decoding with Adaptive Layer Parallelism","created":"2025-06-04","cited_by_count":7,"area":"lr"},{"id":"2503.03340","title":"EnigmaToM: Improve LLMs' Theory-of-Mind Reasoning Capabilities with Neural Knowledge Base of Entity States","created":"2025-03-05","cited_by_count":6,"area":"lr"},{"id":"2505.15734","title":"DEBATE, TRAIN, EVOLVE: Self Evolution of Language Model Reasoning","created":"2025-05-21","cited_by_count":6,"area":"lr"},{"id":"2507.18014","title":"Predictive Scaling Laws for Efficient GRPO Training of Large Reasoning Models","created":"2025-07-24","cited_by_count":6,"area":"lr"},{"id":"2509.12434","title":"Building Coding Agents via Entropy-Enhanced Multi-Turn Preference Optimization","created":"2025-09-15","cited_by_count":6,"area":"lr"},{"id":"2601.15316","title":"The Paradigm Shift: A Comprehensive Survey on Large Vision Language Models for Multimodal Fake News Detection","created":"2026-01-16","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":"2407.04212","title":"Smart Vision-Language Reasoners","created":"2024-07-05","cited_by_count":5,"area":"lr"},{"id":"2410.13510","title":"GeoCoder: Solving Geometry Problems by Generating Modular Code through Vision-Language Models","created":"2024-10-17","cited_by_count":5,"area":"lr"},{"id":"2310.05442","title":"Establishing Trustworthiness: Rethinking Tasks and Model Evaluation","created":"2023-10-09","cited_by_count":4,"area":"lr"},{"id":"2402.11997","title":"Remember This Event That Year? Assessing Temporal Information and Reasoning in Large Language Models","created":"2024-02-19","cited_by_count":4,"area":"lr"},{"id":"2508.13968","title":"RotBench: Evaluating Multimodal Large Language Models on Identifying Image Rotation","created":"2025-08-19","cited_by_count":4,"area":"lr"},{"id":"2510.09354","title":"Logit Arithmetic Elicits Long Reasoning Capabilities Without Training","created":"2025-10-10","cited_by_count":4,"area":"lr"},{"id":"2512.01222","title":"Unsupervised decoding of encoded reasoning using language model interpretability","created":"2025-12-01","cited_by_count":4,"area":"lr"},{"id":"2604.08457","title":"CrashSight: A Phase-Aware, Infrastructure-Centric Video Benchmark for Traffic Crash Scene Understanding and Reasoning","created":"2026-04-09","cited_by_count":4,"area":"lr"},{"id":"2605.04913","title":"Rethinking Local Learning: A Cheaper and Faster Recipe for LLM Post-Training","created":"2026-05-06","cited_by_count":4,"area":"lr"},{"id":"2605.14075","title":"Rethinking Layer Relevance in Large Language Models Beyond Cosine Similarity","created":"2026-05-13","cited_by_count":4,"area":"lr"},{"id":"2312.14870","title":"Numerical Reasoning for Financial Reports","created":"2023-12-22","cited_by_count":3,"area":"lr"},{"id":"2405.13057","title":"Can Github issues be solved with Tree Of Thoughts?","created":"2024-05-20","cited_by_count":3,"area":"lr"},{"id":"2410.18856","title":"Entry-level guide to the use of large language models for medical research","created":"2024-10-24","cited_by_count":3,"area":"lr"},{"id":"2412.15594","title":"Template-Driven LLM-Paraphrased Framework for Tabular Math Word Problem Generation","created":"2024-12-20","cited_by_count":3,"area":"lr"},{"id":"2505.24409","title":"When Language Shapes Thought: Cross-Lingual Transfer of Factual Knowledge in Question Answering","created":"2025-05-30","cited_by_count":3,"area":"lr"},{"id":"2507.08833","title":"LoRA Is Slower Than You Think","created":"2025-07-06","cited_by_count":3,"area":"lr"},{"id":"2512.23292","title":"Agentic Physical AI toward a Domain-Specific Foundation Model for Energy Systems: A Case Study on Nuclear Reactor Control","created":"2025-12-29","cited_by_count":3,"area":"lr"},{"id":"2602.01997","title":"On the Limits of Layer Pruning for Generative Reasoning in Large Language Models","created":"2026-02-02","cited_by_count":3,"area":"lr"},{"id":"2602.02136","title":"Mitigating Safety Tax via Distribution-Grounded Refinement in Large Reasoning Models","created":"2026-02-02","cited_by_count":3,"area":"lr"},{"id":"2606.19172","title":"User as Engram: Internalizing Per-User Memory as Local Parametric Edits","created":"2026-06-17","cited_by_count":3,"area":"lr"},{"id":"2410.06547","title":"TuringQ: Benchmarking AI Comprehension in Theory of Computation","created":"2024-10-09","cited_by_count":2,"area":"lr"},{"id":"2505.04880","title":"Symbolic Analysis of Grover Search Algorithm via Chain-of-Thought Reasoning and Quantum-Native Tokenization","created":"2025-05-08","cited_by_count":2,"area":"lr"},{"id":"2507.12759","title":"Logit Arithmetic Elicits Long Reasoning Capabilities Without Training","created":"2025-07-17","cited_by_count":2,"area":"lr"},{"id":"2508.18579","title":"DrugReasoner: Interpretable Drug Approval Prediction with a Reasoning-augmented Language Model","created":"2025-08-26","cited_by_count":2,"area":"lr"},{"id":"2509.08105","title":"MERLIN: Multi-Stage Curriculum Alignment for Multilingual Encoder-LLM Integration in Cross-Lingual Reasoning","created":"2025-09-09","cited_by_count":2,"area":"lr"},{"id":"2510.10454","title":"Traj-CoA: Patient Trajectory Modeling via Chain-of-Agents for Lung Cancer Risk Prediction","created":"2025-10-12","cited_by_count":2,"area":"lr"},{"id":"2510.23337","title":"BaZi-Based Character Simulation Benchmark: Evaluating AI on Temporal and Persona Reasoning","created":"2025-10-27","cited_by_count":2,"area":"lr"},{"id":"2511.15694","title":"The Impact of Quantization on Large Reasoning Model Reinforcement Learning","created":"2025-11-19","cited_by_count":2,"area":"lr"},{"id":"2601.19942","title":"Latent Object Permanence: Topological Phase Transitions, Free-Energy Principles, and Renormalization Group Flows in Deep Transformer Manifolds","created":"2026-01-16","cited_by_count":2,"area":"lr"},{"id":"2602.13595","title":"The Quantization Trap: Breaking Linear Scaling Laws in Multi-Hop Reasoning","created":"2026-02-14","cited_by_count":2,"area":"lr"},{"id":"2604.18364","title":"Training and Agentic Inference Strategies for LLM-based Manim Animation Generation","created":"2026-04-20","cited_by_count":2,"area":"lr"},{"id":"2605.05802","title":"Selective Rollout: Mid-Trajectory Termination for Multi-Sample Agent RL","created":"2026-05-07","cited_by_count":2,"area":"lr"}],"next_cursor":"100"}