{"total":107,"rows":[{"id":"2403.07974","title":"LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code","created":"2024-03-12","cited_by_count":2004,"area":"lr"},{"id":"2409.04109","title":"Can LLMs Generate Novel Research Ideas? A Large-Scale Human Study with 100+ NLP Researchers","created":"2024-09-06","cited_by_count":363,"area":"agents"},{"id":"2402.10200","title":"Chain-of-Thought Reasoning Without Prompting","created":"2024-02-15","cited_by_count":210,"area":"lr"},{"id":"2405.11403","title":"MapCoder: Multi-Agent Code Generation for Competitive Problem Solving","created":"2024-05-18","cited_by_count":177,"area":"lr"},{"id":"2310.15164","title":"LINC: A Neurosymbolic Approach for Logical Reasoning by Combining Language Models with First-Order Logic Provers","created":"2023-10-23","cited_by_count":168,"area":"lr"},{"id":"2402.03620","title":"Self-Discover: Large Language Models Self-Compose Reasoning Structures","created":"2024-02-06","cited_by_count":110,"area":"lr"},{"id":"2406.04271","title":"Buffer of Thoughts: Thought-Augmented Reasoning with Large Language Models","created":"2024-06-06","cited_by_count":91,"area":"lr"},{"id":"2502.12018","title":"Atom of Thoughts for Markov LLM Test-Time Scaling","created":"2025-02-17","cited_by_count":54,"area":"lr"},{"id":"2407.12994","title":"A Survey of Prompt Engineering Methods in Large Language Models for Different NLP Tasks","created":"2024-07-17","cited_by_count":47,"area":null},{"id":"2406.01940","title":"Process-Driven Autoformalization in Lean 4","created":"2024-06-04","cited_by_count":45,"area":"lr"},{"id":"2401.16467","title":"ReGAL: Refactoring Programs to Discover Generalizable Abstractions","created":"2024-01-29","cited_by_count":36,"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":"2504.18875","title":"Generative to Agentic AI: Survey, Conceptualization, and Challenges","created":"2025-04-26","cited_by_count":33,"area":"agents"},{"id":"2502.05664","title":"CODESIM: Multi-Agent Code Generation and Problem Solving through Simulation-Driven Planning and Debugging","created":"2025-02-08","cited_by_count":32,"area":"agents"},{"id":"2405.16802","title":"AutoPSV: Automated Process-Supervised Verifier","created":"2024-05-27","cited_by_count":30,"area":"lr"},{"id":"2406.13975","title":"MR-Ben: A Meta-Reasoning Benchmark for Evaluating System-2 Thinking in LLMs","created":"2024-06-20","cited_by_count":30,"area":"lr"},{"id":"2406.11698","title":"Meta Reasoning for Large Language Models","created":"2024-06-17","cited_by_count":29,"area":"lr"},{"id":"2410.14826","title":"SPRIG: Improving Large Language Model Performance by System Prompt Optimization","created":"2024-10-18","cited_by_count":29,"area":null},{"id":"2412.00821","title":"Improving Physics Reasoning in Large Language Models Using Mixture of Refinement Agents","created":"2024-12-01","cited_by_count":24,"area":"lr"},{"id":"2506.17088","title":"Chain-of-Thought Prompting Obscures Hallucination Cues in Large Language Models: An Empirical Evaluation","created":"2025-06-20","cited_by_count":21,"area":"lr"},{"id":"2405.03146","title":"Quantifying the Capabilities of LLMs across Scale and Precision","created":"2024-05-06","cited_by_count":19,"area":null},{"id":"2311.09263","title":"Auto-ICL: In-Context Learning without Human Supervision","created":"2023-11-15","cited_by_count":18,"area":null},{"id":"2602.09794","title":"Learning Global Hypothesis Space for Enhancing Synergistic Reasoning Chain","created":"2026-02-10","cited_by_count":17,"area":"lr"},{"id":"2510.06077","title":"When Thinking Drifts: Evidential Grounding for Robust Video Reasoning","created":"2025-10-07","cited_by_count":16,"area":null},{"id":"2403.19094","title":"Learning From Correctness Without Prompting Makes LLM Efficient Reasoner","created":"2024-03-28","cited_by_count":15,"area":"lr"},{"id":"2505.04843","title":"Large Language Models are Autonomous Cyber Defenders","created":"2025-05-07","cited_by_count":15,"area":null},{"id":"2503.04554","title":"Compositional Translation: A Novel LLM-based Approach for Low-resource Machine Translation","created":"2025-03-06","cited_by_count":14,"area":null},{"id":"2402.05785","title":"Limits of Transformer Language Models on Learning to Compose Algorithms","created":"2024-02-08","cited_by_count":13,"area":null},{"id":"2402.12370","title":"AnaloBench: Benchmarking the Identification of Abstract and Long-context Analogies","created":"2024-02-19","cited_by_count":13,"area":null},{"id":"2403.08211","title":"Large Language Models are Contrastive Reasoners","created":"2024-03-13","cited_by_count":11,"area":"lr"},{"id":"2410.08696","title":"AMPO: Automatic Multi-Branched Prompt Optimization","created":"2024-10-11","cited_by_count":11,"area":null},{"id":"2506.10948","title":"Execution Guided Line-by-Line Code Generation","created":"2025-06-12","cited_by_count":10,"area":null},{"id":"2508.07479","title":"Positional Biases Shift as Inputs Approach Context Window Limits","created":"2025-08-10","cited_by_count":9,"area":null},{"id":"2404.12728","title":"Relevant or Random: Can LLMs Truly Perform Analogical Reasoning?","created":"2024-04-19","cited_by_count":8,"area":"lr"},{"id":"2401.05787","title":"Chain of Evidences and Evidence to Generate: Prompting for Context Grounded and Retrieval Augmented Reasoning","created":"2024-01-11","cited_by_count":7,"area":"lr"},{"id":"2406.12084","title":"When Reasoning Meets Information Aggregation: A Case Study with Sports Narratives","created":"2024-06-17","cited_by_count":7,"area":"lr"},{"id":"2407.05134","title":"Solving for X and Beyond: Can Large Language Models Solve Complex Math Problems with More-Than-Two Unknowns?","created":"2024-07-06","cited_by_count":7,"area":null},{"id":"2410.17218","title":"Creativity in AI: Progresses and Challenges","created":"2024-10-22","cited_by_count":7,"area":null},{"id":"2505.14479","title":"Reliable Proof Generation with LLMs via Analogical Retrieval and Symbolic Verification: A Case Study in Euclidean Geometry","created":"2025-05-20","cited_by_count":7,"area":"lr"},{"id":"2605.30653","title":"Counterfactual Graph for Multi-Agent LLM Calibration","created":"2026-05-28","cited_by_count":7,"area":"agents"},{"id":"2506.12115","title":"Eliciting Reasoning in Language Models with Cognitive Tools","created":"2025-06-13","cited_by_count":6,"area":"lr"},{"id":"2510.14509","title":"E2Edev: Benchmarking Large Language Models in End-to-End Software Development Task","created":"2025-10-16","cited_by_count":6,"area":null},{"id":"2605.11258","title":"Unlocking LLM Creativity in Science through Analogical Reasoning","created":"2026-05-11","cited_by_count":6,"area":"lr"},{"id":"2401.05190","title":"DCR: Divide-and-Conquer Reasoning for Multi-choice Question Answering with LLMs","created":"2024-01-10","cited_by_count":5,"area":"lr"},{"id":"2406.10786","title":"Evaluating LLMs with Multiple Problems at once","created":"2024-06-16","cited_by_count":5,"area":null},{"id":"2509.20868","title":"StyleBench: Evaluating thinking styles in Large Language Models","created":"2025-09-25","cited_by_count":5,"area":"lr"},{"id":"2311.06985","title":"Large Language Models are In-context Teachers for Knowledge Reasoning","created":"2023-11-12","cited_by_count":4,"area":"lr"},{"id":"2404.00884","title":"Self-Demos: Eliciting Out-of-Demonstration Generalizability in Large Language Models","created":"2024-04-01","cited_by_count":4,"area":null},{"id":"2410.01772","title":"DeFine: Decision-Making with Analogical Reasoning over Factor Profiles","created":"2024-10-02","cited_by_count":4,"area":"lr"},{"id":"2410.21728","title":"Let's Be Self-generated via Step by Step: A Curriculum Learning Approach to Automated Reasoning with Large Language Models","created":"2024-10-29","cited_by_count":4,"area":"lr"},{"id":"2504.07433","title":"From Token to Line: Enhancing Code Generation with a Long-Term Perspective","created":"2025-04-10","cited_by_count":4,"area":null},{"id":"2512.13040","title":"Understanding Structured Financial Data with LLMs: A Case Study on Fraud Detection","created":"2025-12-15","cited_by_count":4,"area":null},{"id":"2604.06794","title":"GCoT-Decoding: Unlocking Deep Reasoning Paths for Universal Question Answering","created":"2026-04-08","cited_by_count":4,"area":"lr"},{"id":"2411.02666","title":"From Twitter to Reasoner: Understand Mobility Travel Modes and Sentiment Using Large Language Models","created":"2024-11-04","cited_by_count":3,"area":"lr"},{"id":"2501.07892","title":"Leveraging Metamemory Agent for Enhanced Data-Free Code Generation in Large Language Models","created":"2025-01-14","cited_by_count":3,"area":"agents"},{"id":"2502.09974","title":"Has My System Prompt Been Used? Large Language Model Prompt Membership Inference","created":"2025-02-14","cited_by_count":3,"area":"safety"},{"id":"2503.05944","title":"Enhancing Reasoning with Collaboration and Memory","created":"2025-03-07","cited_by_count":3,"area":"lr"},{"id":"2507.00606","title":"Mixture of Reasonings: Teach Large Language Models to Reason with Adaptive Strategies","created":"2025-07-01","cited_by_count":3,"area":"lr"},{"id":"2509.17489","title":"MapCoder-Lite: Distilling Multi-Agent Coding into a Single Small LLM","created":"2025-09-22","cited_by_count":3,"area":"agents"},{"id":"2512.02841","title":"Cross-Lingual Prompt Steerability: Towards Accurate and Robust LLM Behavior across Languages","created":"2025-12-02","cited_by_count":3,"area":null},{"id":"2404.01961","title":"Team UTSA-NLP at SemEval 2024 Task 5: Prompt Ensembling for Argument Reasoning in Civil Procedures with GPT4","created":"2024-04-02","cited_by_count":2,"area":null},{"id":"2411.01307","title":"Can Multimodal Large Language Model Think Analogically?","created":"2024-11-02","cited_by_count":2,"area":"lr"},{"id":"2501.12385","title":"Audio Texture Manipulation by Exemplar-Based Analogy","created":"2025-01-21","cited_by_count":2,"area":null},{"id":"2501.12651","title":"The potential -- and the pitfalls -- of using pre-trained language models as cognitive science theories","created":"2025-01-22","cited_by_count":2,"area":null},{"id":"2502.04689","title":"Improving Language Models with Intentional Analysis","created":"2025-02-07","cited_by_count":2,"area":null},{"id":"2502.15134","title":"Chain-of-Rank: Enhancing Large Language Models for Domain-Specific RAG in Edge Device","created":"2025-02-21","cited_by_count":2,"area":"rag"},{"id":"2503.24190","title":"Implicit In-Context Learning: Evidence from Artificial Language Experiments","created":"2025-03-31","cited_by_count":2,"area":null},{"id":"2506.19095","title":"Baba is LLM: Reasoning in a Game with Dynamic Rules","created":"2025-06-23","cited_by_count":2,"area":"lr"},{"id":"2508.05619","title":"The Missing Reward: Active Inference in the Era of Experience","created":"2025-08-07","cited_by_count":2,"area":"alignment"},{"id":"2510.08804","title":"MOSAIC: Multi-agent Orchestration for Task-Intelligent Scientific Coding","created":"2025-10-09","cited_by_count":2,"area":"agents"},{"id":"2510.17045","title":"Video Reasoning without Training","created":"2025-10-19","cited_by_count":2,"area":"lr"},{"id":"2511.13118","title":"Extracting Events Like Code: A Multi-Agent Programming Framework for Zero-Shot Event Extraction","created":"2025-11-17","cited_by_count":2,"area":"agents"},{"id":"2401.15724","title":"RE-GAINS & EnChAnT: Intelligent Tool Manipulation Systems For Enhanced Query Responses","created":"2024-01-28","cited_by_count":1,"area":null},{"id":"2405.18682","title":"Can GPT Redefine Medical Understanding? Evaluating GPT on Biomedical Machine Reading Comprehension","created":"2024-05-29","cited_by_count":1,"area":null},{"id":"2406.13632","title":"DoubleDipper: Improving Long-Context LLMs via Context Recycling","created":"2024-06-19","cited_by_count":1,"area":null},{"id":"2409.01344","title":"Pairing Analogy-Augmented Generation with Procedural Memory for Procedural Q&A","created":"2024-09-02","cited_by_count":1,"area":null},{"id":"2410.19221","title":"Can Stories Help LLMs Reason? Curating Information Space Through Narrative","created":"2024-10-25","cited_by_count":1,"area":"lr"},{"id":"2412.05023","title":"Steps are all you need: Rethinking STEM Education with Prompt Engineering","created":"2024-12-06","cited_by_count":1,"area":"lr"},{"id":"2502.03080","title":"IAO Prompting: Making Knowledge Flow Explicit in LLMs through Structured Reasoning Templates","created":"2025-02-05","cited_by_count":1,"area":"lr"},{"id":"2505.07005","title":"Explainable AI the Latest Advancements and New Trends","created":"2025-05-11","cited_by_count":1,"area":null},{"id":"2509.12611","title":"Analogy-Driven Financial Chain-of-Thought (AD-FCoT): A Prompting Approach for Financial Sentiment Analysis","created":"2025-09-16","cited_by_count":1,"area":"lr"},{"id":"2510.22312","title":"LacMaterial: Large Language Models as Analogical Chemists for Materials Discovery","created":"2025-10-25","cited_by_count":1,"area":"lr"},{"id":"2511.10441","title":"Analogical Structure, Minimal Contextual Cues and Contrastive Distractors: Input Design for Sample-Efficient Linguistic Rule Induction","created":"2025-11-13","cited_by_count":1,"area":null},{"id":"2511.12797","title":"Genomic Next-Token Predictors are In-Context Learners","created":"2025-11-16","cited_by_count":1,"area":null},{"id":"2602.03542","title":"Can Large Language Models Generalize Procedures Across Representations?","created":"2026-02-03","cited_by_count":1,"area":null},{"id":"2604.15972","title":"Weak-Link Optimization for Multi-Agent Reasoning and Collaboration","created":"2026-04-17","cited_by_count":1,"area":"lr"},{"id":"2501.00562","title":"An Overview and Discussion on Using Large Language Models for Implementation Generation of Solutions to Open-Ended Problems","created":"2024-12-31","cited_by_count":0,"area":null},{"id":"2503.21544","title":"SWI: Speaking with Intent in Large Language Models","created":"2025-03-27","cited_by_count":0,"area":null},{"id":"2504.18839","title":"Detect, Explain, Escalate: Sustainable Dialogue Breakdown Management for LLM Agents","created":"2025-04-26","cited_by_count":0,"area":"agents"},{"id":"2506.21211","title":"$T^3$: Multi-level Tree-based Automatic Program Repair with Large Language Models","created":"2025-06-26","cited_by_count":0,"area":"lr"},{"id":"2507.23170","title":"BAR Conjecture: the Feasibility of Inference Budget-Constrained LLM Services with Authenticity and Reasoning","created":"2025-07-31","cited_by_count":0,"area":"lr"},{"id":"2508.19603","title":"CompLex: Music Theory Lexicon Constructed by Autonomous Agents for Automatic Music Generation","created":"2025-08-27","cited_by_count":0,"area":null},{"id":"2509.08910","title":"PromptGuard: An Orchestrated Prompting Framework for Principled Synthetic Text Generation for Vulnerable Populations using LLMs with Enhanced Safety, Fairness, and Controllability","created":"2025-09-10","cited_by_count":0,"area":null},{"id":"2510.22978","title":"Reasoning About Reasoning: Towards Informed and Reflective Use of LLM Reasoning in HCI","created":"2025-10-27","cited_by_count":0,"area":"lr"},{"id":"2511.14813","title":"DEVAL: A Framework for Evaluating and Improving the Derivation Capability of Large Language Models","created":"2025-11-18","cited_by_count":0,"area":"lr"},{"id":"2511.17036","title":"Do Vision-Language Models Understand Visual Persuasiveness? A Diagnosis via Visual Persuasive Factors","created":"2025-11-21","cited_by_count":0,"area":"mllm"},{"id":"2511.20471","title":"Universe of Thoughts: Enabling Creative Reasoning with Large Language Models","created":"2025-11-25","cited_by_count":0,"area":"lr"},{"id":"2601.08846","title":"Directional Attractors in LLM Reasoning: How Similarity Retrieval Steers Iterative Summarization Based Reasoning","created":"2025-12-22","cited_by_count":0,"area":"lr"},{"id":"2603.10294","title":"Simulation-in-the-Reasoning (SiR): A Conceptual Framework for Empirically Grounded AI in Autonomous Transportation","created":"2026-03-11","cited_by_count":0,"area":"lr"},{"id":"2603.19066","title":"Large Language Models provide support for the parallelogram theory of analogy","created":"2026-03-19","cited_by_count":0,"area":null}],"next_cursor":"100"}