{"total":87,"rows":[{"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,"area":"lr"},{"id":"2311.04850","title":"Rethinking Benchmark and Contamination for Language Models with Rephrased Samples","created":"2023-11-08","cited_by_count":195,"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":"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":"2311.11797","title":"Igniting Language Intelligence: The Hitchhiker's Guide From Chain-of-Thought Reasoning to Language Agents","created":"2023-11-20","cited_by_count":72,"area":"lr"},{"id":"2506.17267","title":"CF-VLM:CounterFactual Vision-Language Fine-tuning","created":"2025-06-10","cited_by_count":59,"area":"lr"},{"id":"2410.05695","title":"Unlocking the Capabilities of Thought: A Reasoning Boundary Framework to Quantify and Optimize Chain-of-Thought","created":"2024-10-08","cited_by_count":56,"area":"lr"},{"id":"2407.14507","title":"Internal Consistency and Self-Feedback in Large Language Models: A Survey","created":"2024-07-19","cited_by_count":50,"area":"lr"},{"id":"2403.16437","title":"Reasoning Runtime Behavior of a Program with LLM: How Far Are We?","created":"2024-03-25","cited_by_count":45,"area":"lr"},{"id":"2503.02390","title":"ReSo: A Reward-driven Self-organizing LLM-based Multi-Agent System for Reasoning Tasks","created":"2025-03-04","cited_by_count":31,"area":"lr"},{"id":"2504.09946","title":"Assessing Judging Bias in Large Reasoning Models: An Empirical Study","created":"2025-04-14","cited_by_count":30,"area":"lr"},{"id":"2405.04669","title":"Towards a Theoretical Understanding of the 'Reversal Curse' via Training Dynamics","created":"2024-05-07","cited_by_count":27,"area":"lr"},{"id":"2406.09072","title":"Living in the Moment: Can Large Language Models Grasp Co-Temporal Reasoning?","created":"2024-06-13","cited_by_count":25,"area":"lr"},{"id":"2510.02837","title":"Beyond the Final Answer: Evaluating the Reasoning Trajectories of Tool-Augmented Agents","created":"2025-10-03","cited_by_count":24,"area":"lr"},{"id":"2412.15118","title":"Reasoning Through Execution: Unifying Process and Outcome Rewards for Code Generation","created":"2024-12-19","cited_by_count":21,"area":"lr"},{"id":"2403.03636","title":"SheetAgent: Towards A Generalist Agent for Spreadsheet Reasoning and Manipulation via Large Language Models","created":"2024-03-06","cited_by_count":17,"area":"lr"},{"id":"2510.13654","title":"Rethinking Evaluation in the Era of Time Series Foundation Models: (Un)known Information Leakage Challenges","created":"2025-10-15","cited_by_count":16,"area":"lr"},{"id":"2406.11288","title":"MFC-Bench: Benchmarking Multimodal Fact-Checking with Large Vision-Language Models","created":"2024-06-17","cited_by_count":15,"area":"lr"},{"id":"2506.04088","title":"Multimodal Tabular Reasoning with Privileged Structured Information","created":"2025-06-04","cited_by_count":15,"area":"lr"},{"id":"2311.11567","title":"InfiMM-Eval: Complex Open-Ended Reasoning Evaluation For Multi-Modal Large Language Models","created":"2023-11-20","cited_by_count":14,"area":"lr"},{"id":"2405.20834","title":"Retrieval Meets Reasoning: Even High-school Textbook Knowledge Benefits Multimodal Reasoning","created":"2024-05-31","cited_by_count":14,"area":"lr"},{"id":"2502.09192","title":"Thinking beyond the anthropomorphic paradigm benefits LLM research","created":"2025-02-13","cited_by_count":14,"area":"lr"},{"id":"2504.15077","title":"Think2SQL: Reinforce LLM Reasoning Capabilities for Text2SQL","created":"2025-04-21","cited_by_count":14,"area":"lr"},{"id":"2406.16308","title":"Anomaly Detection of Tabular Data Using LLMs","created":"2024-06-24","cited_by_count":12,"area":"lr"},{"id":"2505.14404","title":"ViC-Bench: Benchmarking Visual-Interleaved Chain-of-Thought Capability in MLLMs with Free-Style Intermediate State Representations","created":"2025-05-20","cited_by_count":12,"area":"lr"},{"id":"2402.13602","title":"Hybrid Reasoning Based on Large Language Models for Autonomous Car Driving","created":"2024-02-21","cited_by_count":11,"area":"lr"},{"id":"2406.15859","title":"LLM-Powered Explanations: Unraveling Recommendations Through Subgraph Reasoning","created":"2024-06-22","cited_by_count":10,"area":"lr"},{"id":"2410.07114","title":"System 2 thinking in OpenAI's o1-preview model: Near-perfect performance on a mathematics exam","created":"2024-09-19","cited_by_count":10,"area":"lr"},{"id":"2411.11496","title":"Safe + Safe = Unsafe? Exploring How Safe Images Can Be Exploited to Jailbreak Large Vision-Language Models","created":"2024-11-18","cited_by_count":10,"area":"lr"},{"id":"2501.15147","title":"A Causality-aware Paradigm for Evaluating Creativity of Multimodal Large Language Models","created":"2025-01-25","cited_by_count":10,"area":"lr"},{"id":"2505.13115","title":"Benchmarking and Confidence Evaluation of LALMs For Temporal Reasoning","created":"2025-05-19","cited_by_count":10,"area":"lr"},{"id":"2506.18810","title":"ConciseHint: Boosting Efficient Reasoning via Continuous Concise Hints during Generation","created":"2025-06-23","cited_by_count":10,"area":"lr"},{"id":"2412.20662","title":"Enhancing Table Recognition with Vision LLMs: A Benchmark and Neighbor-Guided Toolchain Reasoner","created":"2024-12-30","cited_by_count":9,"area":"lr"},{"id":"2503.04783","title":"Comparative Analysis Based on DeepSeek, ChatGPT, and Google Gemini: Features, Techniques, Performance, Future Prospects","created":"2025-02-25","cited_by_count":9,"area":"lr"},{"id":"2505.22959","title":"LLM-based HSE Compliance Assessment: Benchmark, Performance, and Advancements","created":"2025-05-29","cited_by_count":9,"area":"lr"},{"id":"2411.03455","title":"Watson: A Cognitive Observability Framework for the Reasoning of LLM-Powered Agents","created":"2024-11-05","cited_by_count":8,"area":"lr"},{"id":"2506.06211","title":"PuzzleWorld: A Benchmark for Multimodal, Open-Ended Reasoning in Puzzlehunts","created":"2025-06-06","cited_by_count":8,"area":"lr"},{"id":"2601.22588","title":"Rethinking LLM-as-a-Judge: Representation-as-a-Judge with Small Language Models via Semantic Capacity Asymmetry","created":"2026-01-30","cited_by_count":8,"area":"lr"},{"id":"2505.08189","title":"DSADF: Thinking Fast and Slow for Decision Making","created":"2025-05-13","cited_by_count":7,"area":"lr"},{"id":"2507.02822","title":"SynapseRoute: An Auto-Route Switching Framework on Dual-State Large Language Model","created":"2025-07-03","cited_by_count":7,"area":"lr"},{"id":"2511.14366","title":"ATLAS: A High-Difficulty, Multidisciplinary Benchmark for Frontier Scientific Reasoning","created":"2025-11-18","cited_by_count":6,"area":"lr"},{"id":"2601.03320","title":"Ratio-Variance Regularized Policy Optimization for Efficient LLM Fine-tuning","created":"2026-01-06","cited_by_count":6,"area":"lr"},{"id":"2603.05900","title":"Reference-guided Policy Optimization for Molecular Optimization via LLM Reasoning","created":"2026-03-06","cited_by_count":6,"area":"lr"},{"id":"2410.14198","title":"Supervised Chain of Thought","created":"2024-10-18","cited_by_count":5,"area":"lr"},{"id":"2506.08768","title":"AraReasoner: Evaluating Reasoning-Based LLMs for Arabic NLP","created":"2025-06-10","cited_by_count":5,"area":"lr"},{"id":"2509.03906","title":"Toward Clinically Explainable AI for Medical Diagnosis: A Foundation Model with Human-Compatible Reasoning via Reinforcement Learning","created":"2025-09-04","cited_by_count":5,"area":"lr"},{"id":"2503.21735","title":"GateLens: A Reasoning-Enhanced LLM Agent for Automotive Software Release Analytics","created":"2025-03-27","cited_by_count":4,"area":"lr"},{"id":"2511.06346","title":"LPFQA: A Long-Tail Professional Forum-based Benchmark for LLM Evaluation","created":"2025-11-09","cited_by_count":4,"area":"lr"},{"id":"2401.06603","title":"Mutual Enhancement of Large Language and Reinforcement Learning Models through Bi-Directional Feedback Mechanisms: A Planning Case Study","created":"2024-01-12","cited_by_count":3,"area":"lr"},{"id":"2405.13036","title":"Can formal argumentative reasoning enhance LLMs performances?","created":"2024-05-16","cited_by_count":3,"area":"lr"},{"id":"2410.03062","title":"Image First or Text First? Optimising the Sequencing of Modalities in Large Language Model Prompting and Reasoning Tasks","created":"2024-10-04","cited_by_count":3,"area":"lr"},{"id":"2506.10209","title":"TTT-Bench: A Benchmark for Evaluating Reasoning Ability with Simple and Novel Tic-Tac-Toe-style Games","created":"2025-06-11","cited_by_count":3,"area":"lr"},{"id":"2510.10592","title":"A Layered Intuition -- Method Model with Scope Extension for LLM Reasoning","created":"2025-10-12","cited_by_count":3,"area":"lr"},{"id":"2601.13887","title":"Human Simulation Computation: A Human-Inspired Framework for Adaptive AI Systems","created":"2026-01-20","cited_by_count":3,"area":"lr"},{"id":"2602.03061","title":"Evaluating LLMs When They Do Not Know the Answer: Statistical Evaluation of Mathematical Reasoning via Comparative Signals","created":"2026-02-03","cited_by_count":3,"area":"lr"},{"id":"2604.04942","title":"TDA-RC: Task-Driven Alignment for Knowledge-Based Reasoning Chains in Large Language Models","created":"2026-03-13","cited_by_count":3,"area":"lr"},{"id":"2412.15177","title":"Critical-Questions-of-Thought: Steering LLM reasoning with Argumentative Querying","created":"2024-12-19","cited_by_count":2,"area":"lr"},{"id":"2504.15188","title":"Synergistic Weak-Strong Collaboration by Aligning Preferences","created":"2025-04-21","cited_by_count":2,"area":"lr"},{"id":"2603.02239","title":"Engineering Reasoning and Instruction (ERI) Benchmark: A Large Taxonomy-driven Dataset for Foundation Models and Agents","created":"2026-02-16","cited_by_count":2,"area":"lr"},{"id":"2605.29310","title":"Rubric-Guided Process Reward for Stepwise Model Routing","created":"2026-05-28","cited_by_count":2,"area":"lr"},{"id":"2308.01936","title":"Why Do We Need Neuro-symbolic AI to Model Pragmatic Analogies?","created":"2023-08-02","cited_by_count":1,"area":"lr"},{"id":"2503.03669","title":"Attentive Reasoning Queries: A Systematic Method for Optimizing Instruction-Following in Large Language Models","created":"2025-03-05","cited_by_count":1,"area":"lr"},{"id":"2503.13530","title":"Cognitive Activation and Chaotic Dynamics in Large Language Models: A Quasi-Lyapunov Analysis of Reasoning Mechanisms","created":"2025-03-15","cited_by_count":1,"area":"lr"},{"id":"2505.04914","title":"Enigme: Generative Text Puzzles for Evaluating Reasoning in Language Models","created":"2025-05-08","cited_by_count":1,"area":"lr"},{"id":"2505.23790","title":"Rethinking the Understanding Ability across LLMs through Mutual Information","created":"2025-05-25","cited_by_count":1,"area":"lr"},{"id":"2507.08339","title":"What Factors Affect LLMs and RLLMs in Financial Question Answering?","created":"2025-07-11","cited_by_count":1,"area":"lr"},{"id":"2511.04432","title":"If I Could Turn Back Time: Temporal Reframing as a Historical Reasoning Task for LLMs","created":"2025-11-06","cited_by_count":1,"area":"lr"},{"id":"2512.05954","title":"SymPyBench: A Dynamic Benchmark for Scientific Reasoning with Executable Python Code","created":"2025-12-05","cited_by_count":1,"area":"lr"},{"id":"2601.06461","title":"VIPER Strike: Defeating Visual Reasoning CAPTCHAs via Structured Vision-Language Inference","created":"2026-01-10","cited_by_count":1,"area":"lr"},{"id":"2604.07035","title":"Unified Deployment-Aware Evaluation of Open Reasoning Language Models","created":"2026-04-08","cited_by_count":1,"area":"lr"},{"id":"2604.15972","title":"Weak-Link Optimization for Multi-Agent Reasoning and Collaboration","created":"2026-04-17","cited_by_count":1,"area":"lr"},{"id":"2605.14754","title":"XDomainBench: Diagnosing Reasoning Collapse in High-Dimensional Scientific Knowledge Composition","created":"2026-05-14","cited_by_count":1,"area":"lr"},{"id":"2406.04800","title":"Zero, Finite, and Infinite Belief History of Theory of Mind Reasoning in Large Language Models","created":"2024-06-07","cited_by_count":0,"area":"lr"},{"id":"2410.22151","title":"Standardization Trends on Safety and Trustworthiness Technology for Advanced AI","created":"2024-10-29","cited_by_count":0,"area":"lr"},{"id":"2508.19376","title":"Fine-Tuning Vision-Language Models for Neutrino Event Analysis in High-Energy Physics Experiments","created":"2025-08-26","cited_by_count":0,"area":"lr"},{"id":"2512.03272","title":"When Do Symbolic Solvers Enhance Reasoning in Large Language Models?","created":"2025-12-02","cited_by_count":0,"area":"lr"},{"id":"2602.01528","title":"Making Bias Non-Predictive: Training Robust LLM Reasoning via Reinforcement Learning","created":"2026-02-02","cited_by_count":0,"area":"lr"},{"id":"2602.02295","title":"EvalQReason: A Framework for Step-Level Reasoning Evaluation in Large Language Models","created":"2026-02-02","cited_by_count":0,"area":"lr"},{"id":"2603.14458","title":"Distilling Reasoning Without Knowledge: A Framework for Reliable LLMs","created":"2026-03-15","cited_by_count":0,"area":"lr"},{"id":"2603.21697","title":"Structured Visual Narratives Undermine Safety Alignment in Multimodal Large Language Models","created":"2026-03-23","cited_by_count":0,"area":"lr"},{"id":"2604.03557","title":"When Do Hallucinations Arise? A Graph Perspective on the Evolution of Path Reuse and Path Compression","created":"2026-04-04","cited_by_count":0,"area":"lr"},{"id":"2604.13371","title":"Empirical Evidence of Complexity-Induced Limits in Large Language Models on Finite Discrete State-Space Problems with Explicit Validity Constraints","created":"2026-04-15","cited_by_count":0,"area":"lr"},{"id":"2604.21479","title":"Frozen LLMs as Map-Aware Spatio-Temporal Reasoners for Vehicle Trajectory Prediction","created":"2026-04-23","cited_by_count":0,"area":"lr"},{"id":"2605.13534","title":"Scaling Retrieval-Augmented Reasoning with Parallel Search and Explicit Merging","created":"2026-05-13","cited_by_count":0,"area":"lr"},{"id":"2605.23165","title":"Autonomous Frontier-Based Exploration with VLM Guidance","created":"2026-05-22","cited_by_count":0,"area":"lr"},{"id":"2608.04670","title":"Easy to Complete, Hard to Choose: Investigating LLM Performance on the ProverbIT Benchmark","created":"2026-08-05","cited_by_count":0,"area":"lr"},{"id":"2609.34211","title":"Behavior-Grounded Semantic Enrichment for Financial Fraud Modeling and Reasoning","created":"2026-09-28","cited_by_count":0,"area":"lr"}],"next_cursor":null}