{"total":109,"rows":[{"id":"2503.16419","title":"Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models","created":"2025-03-20","cited_by_count":464,"area":"lr"},{"id":"2504.09037","title":"A Survey of Frontiers in LLM Reasoning: Inference Scaling, Learning to Reason, and Agentic Systems","created":"2025-04-12","cited_by_count":111,"area":"lr"},{"id":"2504.02234","title":"LLM Social Simulations Are a Promising Research Method","created":"2025-04-03","cited_by_count":99,"area":null},{"id":"2510.17516","title":"SimBench: Benchmarking the Ability of Large Language Models to Simulate Human Behaviors","created":"2025-10-20","cited_by_count":52,"area":null},{"id":"2505.05408","title":"Crosslingual Reasoning through Test-Time Scaling","created":"2025-05-08","cited_by_count":46,"area":"lr"},{"id":"2411.13504","title":"Disentangling Memory and Reasoning Ability in Large Language Models","created":"2024-11-20","cited_by_count":44,"area":"lr"},{"id":"2503.16188","title":"Think or Not Think: A Study of Explicit Thinking in Rule-Based Visual Reinforcement Fine-Tuning","created":"2025-03-20","cited_by_count":44,"area":"lr"},{"id":"2503.03064","title":"Improving LLM-as-a-Judge Inference with the Judgment Distribution","created":"2025-03-04","cited_by_count":37,"area":null},{"id":"2508.01491","title":"The Homogenizing Effect of Large Language Models on Human Expression and Thought","created":"2025-08-02","cited_by_count":35,"area":"lr"},{"id":"2508.13141","title":"OptimalThinkingBench: Evaluating Over and Underthinking in LLMs","created":"2025-08-18","cited_by_count":35,"area":"lr"},{"id":"2501.04961","title":"Demystifying Domain-adaptive Post-training for Financial LLMs","created":"2025-01-09","cited_by_count":24,"area":null},{"id":"2604.05655","title":"LLM Reasoning as Trajectories: Step-Specific Representation Geometry and Correctness Signals","created":"2026-04-07","cited_by_count":24,"area":"lr"},{"id":"2505.24362","title":"Knowing Before Saying: LLM Representations Encode Information About Chain-of-Thought Success Before Completion","created":"2025-05-30","cited_by_count":23,"area":"lr"},{"id":"2603.13285","title":"Brittlebench: Quantifying LLM robustness via prompt sensitivity","created":"2026-02-27","cited_by_count":21,"area":null},{"id":"2512.10941","title":"Mull-Tokens: Modality-Agnostic Latent Thinking","created":"2025-12-11","cited_by_count":19,"area":null},{"id":"2505.17312","title":"AdaReasoner: Adaptive Reasoning Enables More Flexible Thinking in Large Language Models","created":"2025-05-22","cited_by_count":17,"area":"lr"},{"id":"2602.04482","title":"ProAgentBench: Evaluating LLM Agents for Proactive Assistance with Real-World Data","created":"2026-02-04","cited_by_count":16,"area":"agents"},{"id":"2501.09012","title":"Multimodal LLMs Can Reason about Aesthetics in Zero-Shot","created":"2025-01-15","cited_by_count":14,"area":"lr"},{"id":"2505.17968","title":"Are Large Language Models Reliable AI Scientists? Assessing Reverse-Engineering of Black-Box Systems","created":"2025-05-23","cited_by_count":14,"area":null},{"id":"2505.23601","title":"EndoBench: A Comprehensive Evaluation of Multi-Modal Large Language Models for Endoscopy Analysis","created":"2025-05-29","cited_by_count":14,"area":"mllm"},{"id":"2502.16435","title":"Human Cognitive Benchmarks Reveal Foundational Visual Gaps in MLLMs","created":"2025-02-23","cited_by_count":13,"area":null},{"id":"2509.25609","title":"A Framework for Studying AI Agent Behavior: Evidence from Consumer Choice Experiments","created":"2025-09-30","cited_by_count":12,"area":"agents"},{"id":"2603.20882","title":"RubricRAG: Towards Interpretable and Reliable LLM Evaluation via Domain Knowledge Retrieval for Rubric Generation","created":"2026-03-21","cited_by_count":11,"area":null},{"id":"2412.08258","title":"Large Language Models for Scholarly Ontology Generation: An Extensive Analysis in the Engineering Field","created":"2024-12-11","cited_by_count":10,"area":null},{"id":"2503.13401","title":"Levels of Analysis for Large Language Models","created":"2025-03-17","cited_by_count":10,"area":null},{"id":"2506.12301","title":"Unveiling Confirmation Bias in Chain-of-Thought Reasoning","created":"2025-06-14","cited_by_count":10,"area":"lr"},{"id":"2506.19467","title":"Can Reasoning Help Large Language Models Capture Human Annotator Disagreement?","created":"2025-06-24","cited_by_count":10,"area":"lr"},{"id":"2510.07880","title":"Do LLMs Really Need 10+ Thoughts for \"Find the Time 1000 Days Later\"? Towards Structural Understanding of LLM Overthinking","created":"2025-10-09","cited_by_count":10,"area":"lr"},{"id":"2511.07979","title":"Benchmarking Multi-Step Legal Reasoning and Analyzing Chain-of-Thought Effects in Large Language Models","created":"2025-11-11","cited_by_count":10,"area":"lr"},{"id":"2508.19827","title":"Analysing Chain of Thought Dynamics: Active Guidance or Unfaithful Post-hoc Rationalisation?","created":"2025-08-27","cited_by_count":9,"area":"lr"},{"id":"2604.02485","title":"Failing to Falsify: Evaluating and Mitigating Confirmation Bias in Language Models","created":"2026-04-02","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":"2510.19687","title":"Are Large Language Models Sensitive to the Motives Behind Communication?","created":"2025-10-22","cited_by_count":8,"area":null},{"id":"2601.06993","title":"Can Textual Reasoning Improve the Performance of MLLMs on Fine-grained Visual Classification?","created":"2026-01-11","cited_by_count":8,"area":"lr"},{"id":"2602.01816","title":"Seeing Is Believing? A Benchmark for Multimodal Large Language Models on Visual Illusions and Anomalies","created":"2026-02-02","cited_by_count":8,"area":"mllm"},{"id":"2410.24155","title":"Blind Spot Navigation in Large Language Model Reasoning with Thought Space Explorer","created":"2024-10-31","cited_by_count":7,"area":"lr"},{"id":"2504.20434","title":"ARCS: Agentic Retrieval-Augmented Code Synthesis with Iterative Refinement","created":"2025-04-29","cited_by_count":7,"area":"rag"},{"id":"2509.24216","title":"MoVa: Towards Generalizable Classification of Human Morals and Values","created":"2025-09-29","cited_by_count":7,"area":null},{"id":"2510.23182","title":"SI-Bench: Benchmarking Social Intelligence of Large Language Models in Human-to-Human Conversations","created":"2025-10-27","cited_by_count":7,"area":null},{"id":"2504.08120","title":"DeepSeek-R1 vs. o3-mini: How Well can Reasoning LLMs Evaluate MT and Summarization?","created":"2025-04-10","cited_by_count":5,"area":"lr"},{"id":"2505.00147","title":"AdaptMI: Adaptive Skill-based In-context Math Instruction for Small Language Models","created":"2025-04-30","cited_by_count":5,"area":null},{"id":"2505.11584","title":"LLM Agents Are Hypersensitive to Nudges","created":"2025-05-16","cited_by_count":5,"area":"agents"},{"id":"2507.15851","title":"The Other Mind: How Language Models Exhibit Human Temporal Cognition","created":"2025-07-21","cited_by_count":5,"area":null},{"id":"2507.18178","title":"Decoupling Knowledge and Reasoning in LLMs: An Exploration Using Cognitive Dual-System Theory","created":"2025-07-24","cited_by_count":5,"area":"lr"},{"id":"2508.10865","title":"Performance of GPT-5 in Brain Tumor MRI Reasoning","created":"2025-08-14","cited_by_count":5,"area":"lr"},{"id":"2509.07370","title":"PersonaFuse: A Personality Activation-Driven Framework for Enhancing Human-LLM Interactions","created":"2025-09-09","cited_by_count":5,"area":null},{"id":"2511.06168","title":"Chain-of-Thought as a Lens: Evaluating Structured Reasoning Alignment between Human Preferences and Large Language Models","created":"2025-11-09","cited_by_count":5,"area":"lr"},{"id":"2504.04141","title":"Self-Adaptive Cognitive Debiasing for Large Language Models in Decision-Making","created":"2025-04-05","cited_by_count":4,"area":null},{"id":"2505.19025","title":"SQUiD: Synthesizing Relational Databases from Unstructured Text","created":"2025-05-25","cited_by_count":4,"area":null},{"id":"2506.06008","title":"Token Signature: Predicting Chain-of-Thought Gains with Token Decoding Feature in Large Language Models","created":"2025-06-06","cited_by_count":4,"area":"lr"},{"id":"2506.13065","title":"MotiveBench: How Far Are We From Human-Like Motivational Reasoning in Large Language Models?","created":"2025-06-16","cited_by_count":4,"area":"lr"},{"id":"2509.16567","title":"V-CECE: Visual Counterfactual Explanations via Conceptual Edits","created":"2025-09-20","cited_by_count":4,"area":null},{"id":"2510.10930","title":"Evaluating Language Models' Evaluations of Games","created":"2025-10-13","cited_by_count":4,"area":"lr"},{"id":"2601.04505","title":"CircuitLM: A Multi-Agent LLM-Aided Design Framework for Generating Circuit Schematics from Natural Language Prompts","created":"2026-01-08","cited_by_count":4,"area":"agents"},{"id":"2605.20284","title":"JUDO: A Juxtaposed Domain-Oriented Multimodal Reasoner for Industrial Anomaly QA","created":"2026-05-19","cited_by_count":4,"area":"mllm"},{"id":"2502.18791","title":"Can LLMs Help Uncover Insights about LLMs? A Large-Scale, Evolving Literature Analysis of Frontier LLMs","created":"2025-02-26","cited_by_count":3,"area":null},{"id":"2505.23667","title":"Formula-R1: Incentivizing LLM Reasoning over Complex Tables with Numerical Computation via Formula-Driven Reinforcement Learning","created":"2025-05-29","cited_by_count":3,"area":"lr"},{"id":"2412.01340","title":"A 2-step Framework for Automated Literary Translation Evaluation: Its Promises and Pitfalls","created":"2024-12-02","cited_by_count":2,"area":null},{"id":"2412.17794","title":"Memory makes computation universal, remember?","created":"2024-12-23","cited_by_count":2,"area":null},{"id":"2503.24190","title":"Implicit In-Context Learning: Evidence from Artificial Language Experiments","created":"2025-03-31","cited_by_count":2,"area":null},{"id":"2504.03352","title":"StereoDetect: Detecting Stereotypes and Anti-stereotypes the Correct Way Using Social Psychological Underpinnings","created":"2025-04-04","cited_by_count":2,"area":null},{"id":"2505.23059","title":"From Token to Action: State Machine Reasoning to Mitigate Overthinking in Information Retrieval","created":"2025-05-29","cited_by_count":2,"area":"lr"},{"id":"2506.10647","title":"Data Shifts Hurt CoT: A Theoretical Study","created":"2025-06-12","cited_by_count":2,"area":"lr"},{"id":"2509.16765","title":"The Sound of Syntax: Finetuning and Comprehensive Evaluation of Language Models for Speech Pathology","created":"2025-09-20","cited_by_count":2,"area":null},{"id":"2510.12699","title":"Generation Space Size: Understanding and Calibrating Open-Endedness of LLM Generations","created":"2025-10-14","cited_by_count":2,"area":null},{"id":"2510.21007","title":"Can Confidence Estimates Decide When Chain-of-Thought Is Necessary for LLMs?","created":"2025-10-23","cited_by_count":2,"area":"lr"},{"id":"2511.06148","title":"Large Language Models Develop Novel Social Biases Through Adaptive Exploration","created":"2025-11-08","cited_by_count":2,"area":null},{"id":"2601.06600","title":"Probing Multimodal Large Language Models on Cognitive Biases in Chinese Short-Video Misinformation","created":"2026-01-10","cited_by_count":2,"area":"mllm"},{"id":"2602.02103","title":"How Far Ahead Do LLMs Plan? Uncovering the Latent Horizon in Chain-of-Thought Reasoning","created":"2026-02-02","cited_by_count":2,"area":"lr"},{"id":"2602.04742","title":"Inference-Time Reasoning Selectively Reduces Implicit Social Bias in Large Language Models","created":"2026-02-04","cited_by_count":2,"area":"lr"},{"id":"2604.10027","title":"SinkTrack: Attention Sink based Context Anchoring for Large Language Models","created":"2026-04-11","cited_by_count":2,"area":null},{"id":"2605.22873","title":"When Do LLMs Reason? A Dynamical Systems View via Entropy Phase Transitions","created":"2026-05-20","cited_by_count":2,"area":"lr"},{"id":"2507.18857","title":"PrismRAG: Boosting RAG Factuality with Distractor Resilience and Strategized Reasoning","created":"2025-07-25","cited_by_count":1,"area":"lr"},{"id":"2508.04691","title":"Before Humans Join the Team: Diagnosing Coordination Failures in Healthcare Robot Team Simulation","created":"2025-08-06","cited_by_count":1,"area":null},{"id":"2508.13718","title":"Generics and Default Reasoning in Large Language Models","created":"2025-08-19","cited_by_count":1,"area":"lr"},{"id":"2508.18992","title":"Automatic Prompt Optimization with Prompt Distillation","created":"2025-08-26","cited_by_count":1,"area":null},{"id":"2510.23464","title":"Evaluating Large Language Models for Stance Detection on Financial Targets from SEC Filing Reports and Earnings Call Transcripts","created":"2025-10-27","cited_by_count":1,"area":null},{"id":"2512.05765","title":"AGI Requires a Coordination Layer on Top of Pattern Repositories","created":"2025-12-05","cited_by_count":1,"area":null},{"id":"2601.14270","title":"Opening the Black Box: A Survey on the Mechanisms of Multi-Step Reasoning in Large Language Models","created":"2026-01-02","cited_by_count":1,"area":"lr"},{"id":"2602.14404","title":"Boule or Baguette? A Study on Task Topology, Length Generalization, and the Benefit of Reasoning Traces","created":"2026-02-16","cited_by_count":1,"area":"lr"},{"id":"2603.07598","title":"SCA: Segment-Wise CoT Compression with Answer Alignment","created":"2026-03-08","cited_by_count":1,"area":"lr"},{"id":"2603.25960","title":"When Chain-of-Thought Backfires: Evaluating Prompt Sensitivity in Medical Language Models","created":"2026-03-26","cited_by_count":1,"area":"lr"},{"id":"2604.23734","title":"Prism-Reranker: Beyond Relevance Scoring -- Jointly Producing Contributions and Evidence for Agentic Retrieval","created":"2026-04-26","cited_by_count":1,"area":"rag"},{"id":"2605.28123","title":"Risk-aware Selective Prompting for Hallucination Mitigation in Large Vision-Language Models","created":"2026-05-27","cited_by_count":1,"area":"mllm"},{"id":"2607.00672","title":"DART: Difficulty-Adaptive Routing for Zero-Shot Video Temporal Grounding","created":"2026-07-01","cited_by_count":1,"area":null},{"id":"2608.18081","title":"Position: Behavioral Systems Require Behavioral Tests","created":"2026-05-31","cited_by_count":1,"area":"agents"},{"id":"2609.22588","title":"Seeing is not Enough: Vision-Language Models Perceive Evidence but Fail to Act","created":"2026-09-18","cited_by_count":1,"area":"mllm"},{"id":"2509.20805","title":"Few-Shot and Training-Free Review Generation via Conversational Prompting","created":"2025-09-25","cited_by_count":0,"area":null},{"id":"2510.21839","title":"Evaluating ChatGPT's Performance in Classifying Pneumonia from Chest X-Ray Images","created":"2025-10-22","cited_by_count":0,"area":null},{"id":"2511.06522","title":"FractalBench: Diagnosing Visual-Mathematical Reasoning Through Recursive Program Synthesis","created":"2025-11-09","cited_by_count":0,"area":"lr"},{"id":"2603.28731","title":"SAGAI-MID: A Generative AI-Driven Middleware for Dynamic Runtime Interoperability","created":"2026-03-30","cited_by_count":0,"area":null},{"id":"2604.01652","title":"ThinknCheck: Grounded Claim Verification with Compact, Reasoning-Driven, and Interpretable Models","created":"2026-04-02","cited_by_count":0,"area":null},{"id":"2604.08872","title":"How does Chain of Thought decompose complex tasks?","created":"2026-04-10","cited_by_count":0,"area":"lr"},{"id":"2605.03858","title":"MCJudgeBench: A Benchmark for Constraint-Level Judge Evaluation in Multi-Constraint Instruction Following","created":"2026-05-05","cited_by_count":0,"area":null},{"id":"2605.09900","title":"The Gordian Knot for VLMs: Diagrammatic Knot Reasoning as a Hard Benchmark","created":"2026-05-11","cited_by_count":0,"area":"lr"},{"id":"2605.14084","title":"CRANE: Constrained Reasoning Injection for Code Agents via Nullspace Editing","created":"2026-05-13","cited_by_count":0,"area":null},{"id":"2605.20410","title":"Mechanics of Bias and Reasoning: Interpreting the Impact of Chain-of-Thought Prompting on Gender Bias in LLMs","created":"2026-05-19","cited_by_count":0,"area":"lr"},{"id":"2605.24267","title":"DRInQ: Evaluating Conversational Implicature with Controlled Context Variation","created":"2026-05-22","cited_by_count":0,"area":null},{"id":"2605.28215","title":"Explaining is Harder Than Predicting Alone: Evaluating Concept-based Explanations of MLLMs as ICL Visual Classifiers","created":"2026-05-27","cited_by_count":0,"area":"mllm"},{"id":"2606.03217","title":"An Asymptotic Theory of Chain-of-Thought in In-Context Learning","created":"2026-06-02","cited_by_count":0,"area":"lr"}],"next_cursor":"100"}