{"total":127,"rows":[{"id":"2411.10440","title":"LLaVA-CoT: Let Vision Language Models Reason Step-by-Step","created":"2024-11-15","cited_by_count":454,"area":"lr"},{"id":"2503.09567","title":"Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Models","created":"2025-03-12","cited_by_count":384,"area":"lr"},{"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,"area":"wm"},{"id":"2412.18925","title":"HuatuoGPT-o1, Towards Medical Complex Reasoning with LLMs","created":"2024-12-25","cited_by_count":265,"area":"lr"},{"id":"2502.08235","title":"The Danger of Overthinking: Examining the Reasoning-Action Dilemma in Agentic Tasks","created":"2025-02-12","cited_by_count":152,"area":"lr"},{"id":"2411.14405","title":"Marco-o1: Towards Open Reasoning Models for Open-Ended Solutions","created":"2024-11-21","cited_by_count":144,"area":"lr"},{"id":"2504.00993","title":"MedReason: Eliciting Factual Medical Reasoning Steps in LLMs via Knowledge Graphs","created":"2025-04-01","cited_by_count":110,"area":"lr"},{"id":"2504.07128","title":"DeepSeek-R1 Thoughtology: Let's think about LLM Reasoning","created":"2025-04-02","cited_by_count":92,"area":"lr"},{"id":"2508.14111","title":"From AI for Science to Agentic Science: A Survey on Autonomous Scientific Discovery","created":"2025-08-18","cited_by_count":77,"area":"agents"},{"id":"2411.05990","title":"Game-theoretic LLM: Agent Workflow for Negotiation Games","created":"2024-11-08","cited_by_count":56,"area":"agents"},{"id":"2412.11936","title":"A Survey of Mathematical Reasoning in the Era of Multimodal Large Language Model: Benchmark, Method & Challenges","created":"2024-12-16","cited_by_count":55,"area":"lr"},{"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,"area":"lr"},{"id":"2502.06781","title":"Exploring the Limit of Outcome Reward for Learning Mathematical Reasoning","created":"2025-02-10","cited_by_count":52,"area":"lr"},{"id":"2507.14417","title":"Inverse Scaling in Test-Time Compute","created":"2025-07-19","cited_by_count":50,"area":"lr"},{"id":"2501.02765","title":"Visual Large Language Models for Generalized and Specialized Applications","created":"2025-01-06","cited_by_count":36,"area":"mllm"},{"id":"2502.08127","title":"Fino1: On the Transferability of Reasoning-Enhanced LLMs and Reinforcement Learning to Finance","created":"2025-02-12","cited_by_count":35,"area":"lr"},{"id":"2509.03516","title":"Easier Painting Than Thinking: Can Text-to-Image Models Set the Stage, but Not Direct the Play?","created":"2025-09-03","cited_by_count":34,"area":null},{"id":"2504.18875","title":"Generative to Agentic AI: Survey, Conceptualization, and Challenges","created":"2025-04-26","cited_by_count":33,"area":"agents"},{"id":"2502.06776","title":"InSTA: Towards Internet-Scale Training For Agents","created":"2025-02-10","cited_by_count":32,"area":"agents"},{"id":"2503.08506","title":"ReviewAgents: Bridging the Gap Between Human and AI-Generated Paper Reviews","created":"2025-03-11","cited_by_count":32,"area":null},{"id":"2503.04550","title":"Benchmarking Reasoning Robustness in Large Language Models","created":"2025-03-06","cited_by_count":30,"area":"lr"},{"id":"2411.08147","title":"Large Language Models Can Self-Improve in Long-context Reasoning","created":"2024-11-12","cited_by_count":29,"area":"lr"},{"id":"2503.04691","title":"Quantifying the Reasoning Abilities of LLMs on Real-world Clinical Cases","created":"2025-03-06","cited_by_count":29,"area":"lr"},{"id":"2412.03131","title":"DiffKV: Differentiated Memory Management for Large Language Models with Parallel KV Compaction","created":"2024-12-04","cited_by_count":26,"area":"inference"},{"id":"2410.21418","title":"Large Language Models for Manufacturing","created":"2024-10-28","cited_by_count":24,"area":null},{"id":"2503.18132","title":"MathAgent: Leveraging a Mixture-of-Math-Agent Framework for Real-World Multimodal Mathematical Error Detection","created":"2025-03-23","cited_by_count":24,"area":"lr"},{"id":"2502.19559","title":"Stay Focused: Problem Drift in Multi-Agent Debate","created":"2025-02-26","cited_by_count":23,"area":"agents"},{"id":"2504.15716","title":"DianJin-R1: Evaluating and Enhancing Financial Reasoning in Large Language Models","created":"2025-04-22","cited_by_count":22,"area":"lr"},{"id":"2602.13517","title":"Think Deep, Not Just Long: Measuring LLM Reasoning Effort via Deep-Thinking Tokens","created":"2026-02-13","cited_by_count":22,"area":"lr"},{"id":"2504.20115","title":"AutoP2C: An LLM-Based Agent Framework for Code Repository Generation from Multimodal Content in Academic Papers","created":"2025-04-28","cited_by_count":20,"area":"agents"},{"id":"2505.02665","title":"A Survey of Slow Thinking-based Reasoning LLMs using Reinforced Learning and Inference-time Scaling Law","created":"2025-05-05","cited_by_count":19,"area":"lr"},{"id":"2505.22113","title":"THINK-Bench: Evaluating Thinking Efficiency and Chain-of-Thought Quality of Large Reasoning Models","created":"2025-05-28","cited_by_count":19,"area":"lr"},{"id":"2505.11462","title":"Disentangling Reasoning and Knowledge in Medical Large Language Models","created":"2025-05-16","cited_by_count":18,"area":"lr"},{"id":"2502.16268","title":"ThinkBench: Dynamic Out-of-Distribution Evaluation for Robust LLM Reasoning","created":"2025-02-22","cited_by_count":17,"area":"lr"},{"id":"2410.21287","title":"A Systematic Assessment of OpenAI o1-Preview for Higher Order Thinking in Education","created":"2024-10-11","cited_by_count":16,"area":"lr"},{"id":"2503.12918","title":"ThinkPatterns-21k: A Systematic Study on the Impact of Thinking Patterns in LLMs","created":"2025-03-17","cited_by_count":16,"area":"lr"},{"id":"2505.14140","title":"RL of Thoughts: Navigating LLM Reasoning with Inference-time Reinforcement Learning","created":"2025-05-20","cited_by_count":16,"area":"lr"},{"id":"2505.17063","title":"Synthetic Data RL: Task Definition Is All You Need","created":"2025-05-18","cited_by_count":15,"area":"lr"},{"id":"2506.04832","title":"Joint Evaluation of Answer and Reasoning Consistency for Hallucination Detection in Large Reasoning Models","created":"2025-06-05","cited_by_count":14,"area":"lr"},{"id":"2511.07378","title":"Transformers Provably Learn Chain-of-Thought Reasoning with Length Generalization","created":"2025-11-10","cited_by_count":14,"area":"lr"},{"id":"2503.01461","title":"Marco-o1 v2: Towards Widening The Distillation Bottleneck for Reasoning Models","created":"2025-03-03","cited_by_count":13,"area":"lr"},{"id":"2411.11295","title":"Transcending Language Boundaries: Harnessing LLMs for Low-Resource Language Translation","created":"2024-11-18","cited_by_count":12,"area":null},{"id":"2502.07803","title":"Reasoning-as-Logic-Units: Scaling Test-Time Reasoning in Large Language Models Through Logic Unit Alignment","created":"2025-02-05","cited_by_count":12,"area":"lr"},{"id":"2503.00912","title":"HiBench: Benchmarking LLMs Capability on Hierarchical Structure Reasoning","created":"2025-03-02","cited_by_count":12,"area":"lr"},{"id":"2505.21479","title":"Are Language Models Consequentialist or Deontological Moral Reasoners?","created":"2025-05-27","cited_by_count":12,"area":"lr"},{"id":"2411.14461","title":"Towards Next-Generation Medical Agent: How o1 is Reshaping Decision-Making in Medical Scenarios","created":"2024-11-16","cited_by_count":10,"area":"agents"},{"id":"2412.10827","title":"Rethinking Chain-of-Thought from the Perspective of Self-Training","created":"2024-12-14","cited_by_count":10,"area":"lr"},{"id":"2601.23045","title":"The Hot Mess of AI: How Does Misalignment Scale With Model Intelligence and Task Complexity?","created":"2026-01-30","cited_by_count":10,"area":null},{"id":"2410.12376","title":"ShapefileGPT: A Multi-Agent Large Language Model Framework for Automated Shapefile Processing","created":"2024-10-16","cited_by_count":9,"area":"agents"},{"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":"2503.23219","title":"Aurelia: Test-time Reasoning Distillation in Audio-Visual LLMs","created":"2025-03-29","cited_by_count":9,"area":"lr"},{"id":"2502.10308","title":"LLM-Powered Preference Elicitation in Combinatorial Assignment","created":"2025-02-14","cited_by_count":8,"area":null},{"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":"2507.16814","title":"Semi-off-Policy Reinforcement Learning for Vision-Language Slow-Thinking Reasoning","created":"2025-07-22","cited_by_count":8,"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":"2502.12962","title":"Infinite Retrieval: Attention Enhanced LLMs in Long-Context Processing","created":"2025-02-18","cited_by_count":7,"area":"lr"},{"id":"2504.09421","title":"ClinicalGPT-R1: Pushing reasoning capability of generalist disease diagnosis with large language model","created":"2025-04-13","cited_by_count":7,"area":"lr"},{"id":"2505.20971","title":"Reason-Align-Respond: Aligning LLM Reasoning with Knowledge Graphs for KGQA","created":"2025-05-27","cited_by_count":7,"area":"lr"},{"id":"2507.00218","title":"Learning for routing: A guided review of recent developments and future directions","created":"2025-06-30","cited_by_count":7,"area":null},{"id":"2601.08689","title":"QuantEval: A Benchmark for Financial Quantitative Tasks in Large Language Models","created":"2026-01-13","cited_by_count":7,"area":null},{"id":"2410.10858","title":"Reasoning Paths Optimization: Learning to Reason and Explore From Diverse Paths","created":"2024-10-07","cited_by_count":6,"area":"lr"},{"id":"2502.04355","title":"LLM-ProS: Analyzing Large Language Models' Performance in Competitive Problem Solving","created":"2025-02-04","cited_by_count":6,"area":null},{"id":"2504.02810","title":"Generative Evaluation of Complex Reasoning in Large Language Models","created":"2025-04-03","cited_by_count":6,"area":"lr"},{"id":"2504.07357","title":"Revisiting Prompt Optimization with Large Reasoning Models-A Case Study on Event Extraction","created":"2025-04-10","cited_by_count":6,"area":"lr"},{"id":"2508.09893","title":"RAGulating Compliance: A Multi-Agent Knowledge Graph for Regulatory QA","created":"2025-08-13","cited_by_count":6,"area":"agents"},{"id":"2509.19003","title":"Unveiling Chain of Step Reasoning for Vision-Language Models with Fine-grained Rewards","created":"2025-09-23","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":"2412.04774","title":"Foundation Models for Low-Resource Language Education (Vision Paper)","created":"2024-12-06","cited_by_count":5,"area":null},{"id":"2502.10428","title":"Dynamic Chain-of-Thought: Towards Adaptive Deep Reasoning","created":"2025-02-07","cited_by_count":5,"area":"lr"},{"id":"2504.17584","title":"CHIME: A Case for Efficient Long-Context Attention-FC Disaggregated Inference with DIMM-PIM","created":"2025-04-24","cited_by_count":5,"area":"inference"},{"id":"2505.12000","title":"IQBench: How \"Smart'' Are Vision-Language Models? A Study with Human IQ Tests","created":"2025-05-17","cited_by_count":5,"area":"lr"},{"id":"2505.20192","title":"FunReason: Enhancing Large Language Models' Function Calling via Self-Refinement Multiscale Loss and Automated Data Refinement","created":"2025-05-26","cited_by_count":5,"area":"lr"},{"id":"2410.18142","title":"Analyzing Nobel Prize Literature with Large Language Models","created":"2024-10-22","cited_by_count":4,"area":null},{"id":"2411.06198","title":"OpenAI-o1 AB Testing: Does the o1 model really do good reasoning in math problem solving?","created":"2024-11-09","cited_by_count":4,"area":"lr"},{"id":"2411.09111","title":"Reducing Reasoning Costs: The Path of Optimization for Chain of Thought via Sparse Attention Mechanism","created":"2024-11-14","cited_by_count":4,"area":"lr"},{"id":"2502.17848","title":"LR^2Bench: Evaluating Long-chain Reflective Reasoning Capabilities of Large Language Models via Constraint Satisfaction Problems","created":"2025-02-25","cited_by_count":4,"area":"lr"},{"id":"2503.21332","title":"ReFeed: Multi-dimensional Summarization Refinement with Reflective Reasoning on Feedback","created":"2025-03-27","cited_by_count":4,"area":null},{"id":"2505.21538","title":"Caption This, Reason That: VLMs Caught in the Middle","created":"2025-05-24","cited_by_count":4,"area":"lr"},{"id":"2506.07751","title":"AbstRaL: Augmenting LLMs' Reasoning by Reinforcing Abstract Thinking","created":"2025-06-09","cited_by_count":4,"area":"lr"},{"id":"2508.15790","title":"KG-o1: Enhancing Multi-hop Question Answering in Large Language Models via Knowledge Graph Integration","created":"2025-08-12","cited_by_count":4,"area":"lr"},{"id":"2509.07763","title":"What Were You Thinking? An LLM-Driven Large-Scale Study of Refactoring Motivations in Open-Source Projects","created":"2025-09-09","cited_by_count":4,"area":null},{"id":"2512.01925","title":"Rectifying LLM Thought from Lens of Optimization","created":"2025-12-01","cited_by_count":4,"area":"lr"},{"id":"2607.01511","title":"Revisiting Chain-of-Thought Reasoning under Limited Supervision: Semi-supervised Chain-of-Thought Learning","created":"2026-07-01","cited_by_count":4,"area":"lr"},{"id":"2412.05753","title":"Can OpenAI o1 outperform humans in higher-order cognitive thinking?","created":"2024-12-07","cited_by_count":3,"area":null},{"id":"2501.06271","title":"Large Language Models for Bioinformatics","created":"2025-01-10","cited_by_count":3,"area":null},{"id":"2504.05908","title":"PRIMEDrive-CoT: A Precognitive Chain-of-Thought Framework for Uncertainty-Aware Object Interaction in Driving Scene Scenario","created":"2025-04-08","cited_by_count":3,"area":"lr"},{"id":"2506.08488","title":"EtiCor++: Towards Understanding Etiquettical Bias in LLMs","created":"2025-06-10","cited_by_count":3,"area":null},{"id":"2507.22467","title":"Towards Simulating Social Influence Dynamics with LLM-based Multi-agents","created":"2025-07-30","cited_by_count":3,"area":"agents"},{"id":"2510.27469","title":"Diffuse Thinking: Exploring Diffusion Language Models as Efficient Thought Proposers for Reasoning","created":"2025-10-31","cited_by_count":3,"area":"lr"},{"id":"2606.00133","title":"World Models: A Comprehensive Survey of Architectures, Methodologies, Reasoning Paradigms, and Applications","created":"2026-05-28","cited_by_count":3,"area":"wm"},{"id":"2502.06150","title":"Scaling Public Health Text Annotation: Zero-Shot Learning vs. Crowdsourcing for Improved Efficiency and Labeling Accuracy","created":"2025-02-10","cited_by_count":2,"area":null},{"id":"2503.01385","title":"Q-NL Verifier: Leveraging Synthetic Data for Robust Knowledge Graph Question Answering","created":"2025-03-03","cited_by_count":2,"area":"synth"},{"id":"2504.03718","title":"Task-Aware Parameter-Efficient Fine-Tuning of Large Pre-Trained Models at the Edge","created":"2025-03-29","cited_by_count":2,"area":null},{"id":"2504.04042","title":"An Explicit Syllogistic Legal Reasoning Framework for Large Language Models","created":"2025-04-05","cited_by_count":2,"area":"lr"},{"id":"2505.06637","title":"Exploring Multimodal Foundation AI and Expert-in-the-Loop for Sustainable Management of Wild Salmon Fisheries in Indigenous Rivers","created":"2025-05-10","cited_by_count":2,"area":null},{"id":"2505.15242","title":"Adaptive Plan-Execute Framework for Smart Contract Security Auditing","created":"2025-05-21","cited_by_count":2,"area":null},{"id":"2505.17482","title":"From Reasoning to Generalization: Knowledge-Augmented LLMs for ARC Benchmark","created":"2025-05-23","cited_by_count":2,"area":"lr"},{"id":"2506.13886","title":"Investigating the interaction of linguistic and mathematical reasoning in language models using multilingual number puzzles","created":"2025-06-16","cited_by_count":2,"area":"lr"},{"id":"2507.10818","title":"How Robust are LLM-Generated Library Imports? An Empirical Study using Stack Overflow","created":"2025-07-14","cited_by_count":2,"area":null},{"id":"2512.03549","title":"PARC: An Autonomous Self-Reflective Coding Agent for Robust Execution of Long-Horizon Tasks","created":"2025-12-03","cited_by_count":2,"area":"agents"}],"next_cursor":"100"}