{"total":101,"rows":[{"id":"2503.21460","title":"Large Language Model Agent: A Survey on Methodology, Applications and Challenges","created":"2025-03-27","cited_by_count":205,"area":"agents"},{"id":"2404.11584","title":"The Landscape of Emerging AI Agent Architectures for Reasoning, Planning, and Tool Calling: A Survey","created":"2024-04-17","cited_by_count":168,"area":"agents"},{"id":"2404.18824","title":"Benchmarking Benchmark Leakage in Large Language Models","created":"2024-04-29","cited_by_count":106,"area":null},{"id":"2410.15226","title":"On the Diversity of Synthetic Data and its Impact on Training Large Language Models","created":"2024-10-19","cited_by_count":59,"area":"synth"},{"id":"2407.08733","title":"Is Your Model Really A Good Math Reasoner? Evaluating Mathematical Reasoning with Checklist","created":"2024-07-11","cited_by_count":48,"area":"lr"},{"id":"2407.09007","title":"Benchmarking Language Model Creativity: A Case Study on Code Generation","created":"2024-07-12","cited_by_count":40,"area":null},{"id":"2407.01511","title":"CRAB: Cross-environment Agent Benchmark for Multimodal Language Model Agents","created":"2024-07-01","cited_by_count":39,"area":"mllm"},{"id":"2502.17521","title":"Recent Advances in Large Langauge Model Benchmarks against Data Contamination: From Static to Dynamic Evaluation","created":"2025-02-23","cited_by_count":38,"area":null},{"id":"2502.14425","title":"A Survey on Data Contamination for Large Language Models","created":"2025-02-20","cited_by_count":35,"area":null},{"id":"2504.13367","title":"THOUGHTTERMINATOR: Benchmarking, Calibrating, and Mitigating Overthinking in Reasoning Models","created":"2025-04-17","cited_by_count":35,"area":"lr"},{"id":"2411.12498","title":"Enhancing Reasoning Capabilities of LLMs via Principled Synthetic Logic Corpus","created":"2024-11-19","cited_by_count":29,"area":"lr"},{"id":"2412.08972","title":"RuleArena: A Benchmark for Rule-Guided Reasoning with LLMs in Real-World Scenarios","created":"2024-12-12","cited_by_count":27,"area":"lr"},{"id":"2406.17271","title":"DARG: Dynamic Evaluation of Large Language Models via Adaptive Reasoning Graph","created":"2024-06-25","cited_by_count":26,"area":"lr"},{"id":"2406.18966","title":"DataGen: Unified Synthetic Dataset Generation via Large Language Models","created":"2024-06-27","cited_by_count":23,"area":"synth"},{"id":"2503.04149","title":"Dynamic Benchmarking of Reasoning Capabilities in Code Large Language Models Under Data Contamination","created":"2025-03-06","cited_by_count":23,"area":"lr"},{"id":"2410.21259","title":"AutoBench-V: Can Large Vision-Language Models Benchmark Themselves?","created":"2024-10-28","cited_by_count":21,"area":"mllm"},{"id":"2403.04780","title":"Graph-oriented Instruction Tuning of Large Language Models for Generic Graph Mining","created":"2024-03-02","cited_by_count":20,"area":null},{"id":"2505.18882","title":"Personalized Safety in LLMs: A Benchmark and A Planning-Based Agent Approach","created":"2025-05-24","cited_by_count":16,"area":"agents"},{"id":"2503.16402","title":"The Emperor's New Clothes in Benchmarking? A Rigorous Examination of Mitigation Strategies for LLM Benchmark Data Contamination","created":"2025-03-20","cited_by_count":15,"area":null},{"id":"2402.13125","title":"TreeEval: Benchmark-Free Evaluation of Large Language Models through Tree Planning","created":"2024-02-20","cited_by_count":14,"area":null},{"id":"2409.14057","title":"Co-occurrence is not Factual Association in Language Models","created":"2024-09-21","cited_by_count":12,"area":null},{"id":"2505.23495","title":"Diagnosing and Addressing Pitfalls in KG-RAG Datasets: Toward More Reliable Benchmarking","created":"2025-05-29","cited_by_count":12,"area":"lr"},{"id":"2406.04197","title":"DICE: Detecting In-distribution Contamination in LLM's Fine-tuning Phase for Math Reasoning","created":"2024-06-06","cited_by_count":11,"area":"lr"},{"id":"2502.07577","title":"Automated Capability Discovery via Foundation Model Self-Exploration","created":"2025-02-11","cited_by_count":10,"area":null},{"id":"2410.22584","title":"BenchAgents: Multi-Agent Systems for Structured Benchmark Creation","created":"2024-10-29","cited_by_count":9,"area":"agents"},{"id":"2502.15823","title":"InductionBench: LLMs Fail in the Simplest Complexity Class","created":"2025-02-20","cited_by_count":9,"area":null},{"id":"2506.03231","title":"NetArena: Dynamic Benchmarks for AI Agents in Network Automation","created":"2025-06-03","cited_by_count":9,"area":null},{"id":"2602.12966","title":"ProbeLLM: Automating Principled Diagnosis of LLM Failures","created":"2026-02-13","cited_by_count":9,"area":null},{"id":"2409.09318","title":"ODE: Open-Set Evaluation of Hallucinations in Multimodal Large Language Models","created":"2024-09-14","cited_by_count":8,"area":"mllm"},{"id":"2505.18917","title":"Behavior Injection: Preparing Language Models for Reinforcement Learning","created":"2025-05-25","cited_by_count":8,"area":"lr"},{"id":"2502.01683","title":"LLM-Powered Benchmark Factory: Reliable, Generic, and Efficient","created":"2025-02-02","cited_by_count":7,"area":null},{"id":"2505.18102","title":"CapBencher: Give Your LLM Benchmark a Built-in Alarm for Test-Set Overfitting","created":"2025-05-23","cited_by_count":7,"area":null},{"id":"2507.17747","title":"Pretraining on the Test Set Is No Longer All You Need: A Debate-Driven Approach to QA Benchmarks","created":"2025-07-23","cited_by_count":7,"area":null},{"id":"2409.14302","title":"Reliable and diverse evaluation of LLM medical knowledge mastery","created":"2024-09-22","cited_by_count":6,"area":null},{"id":"2503.23361","title":"Discovering Knowledge Deficiencies of Language Models on Massive Knowledge Base","created":"2025-03-30","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":"2506.02648","title":"Truly Assessing Fluid Intelligence of Large Language Models through Dynamic Reasoning Evaluation","created":"2025-06-03","cited_by_count":6,"area":"lr"},{"id":"2507.19219","title":"How Much Do Large Language Model Cheat on Evaluation? Benchmarking Overestimation under the One-Time-Pad-Based Framework","created":"2025-07-25","cited_by_count":6,"area":null},{"id":"2509.23061","title":"Local Success Does Not Compose: Benchmarking Large Language Models for Compositional Formal Verification","created":"2025-09-27","cited_by_count":6,"area":null},{"id":"2510.04311","title":"On the Importance of Task Complexity in Evaluating LLM-Based Multi-Agent Systems","created":"2025-10-05","cited_by_count":6,"area":"agents"},{"id":"2606.06462","title":"Benchmark Everything Everywhere All at Once","created":"2026-06-04","cited_by_count":6,"area":null},{"id":"2503.05049","title":"Dynamic-KGQA: A Scalable Framework for Generating Adaptive Question Answering Datasets","created":"2025-03-06","cited_by_count":5,"area":null},{"id":"2505.22467","title":"Topological Structure Learning Should Be A Research Priority for LLM-Based Multi-Agent Systems","created":"2025-05-28","cited_by_count":5,"area":"agents"},{"id":"2604.10988","title":"WebForge: Breaking the Realism-Reproducibility-Scalability Trilemma in Browser Agent Benchmark","created":"2026-04-13","cited_by_count":5,"area":null},{"id":"2410.11507","title":"TestAgent: Automatic Benchmarking and Exploratory Interaction for Evaluating LLMs in Vertical Domains","created":"2024-10-15","cited_by_count":4,"area":null},{"id":"2411.14062","title":"MMGenBench: Fully Automatically Evaluating LMMs from the Text-to-Image Generation Perspective","created":"2024-11-21","cited_by_count":4,"area":"mllm"},{"id":"2502.12459","title":"Large Language Models Badly Generalize across Option Length, Problem Types, and Irrelevant Noun Replacements","created":"2025-02-18","cited_by_count":4,"area":null},{"id":"2503.01986","title":"Adaptively profiling models with task elicitation","created":"2025-03-03","cited_by_count":4,"area":null},{"id":"2503.04840","title":"Framing the Game: How Context Shapes LLM Decision-Making","created":"2025-03-05","cited_by_count":4,"area":null},{"id":"2510.17725","title":"AcademicEval: Live Long-Context LLM Benchmark","created":"2025-10-20","cited_by_count":4,"area":null},{"id":"2410.07030","title":"Clean Evaluations on Contaminated Visual Language Models","created":"2024-10-09","cited_by_count":3,"area":"mllm"},{"id":"2503.10542","title":"Language Models, Graph Searching, and Supervision Adulteration: When More Supervision is Less and How to Make More More","created":"2025-03-13","cited_by_count":3,"area":null},{"id":"2505.00759","title":"Multimodal Language Models as Text-to-Image Model Evaluators","created":"2025-05-01","cited_by_count":3,"area":"mllm"},{"id":"2506.00963","title":"From Objectives to Questions: A Planning-based Framework for Educational Mathematical Question Generation","created":"2025-06-01","cited_by_count":3,"area":null},{"id":"2507.09701","title":"MCEval: A Dynamic Framework for Fair Multilingual Cultural Evaluation of LLMs","created":"2025-07-13","cited_by_count":3,"area":null},{"id":"2508.06142","title":"SDEval: Safety Dynamic Evaluation for Multimodal Large Language Models","created":"2025-08-08","cited_by_count":3,"area":"mllm"},{"id":"2508.18905","title":"Interactive Evaluation of Large Language Models for Multi-Requirement Software Engineering Tasks","created":"2025-08-26","cited_by_count":3,"area":null},{"id":"2602.00593","title":"Pix2Fact: When Vision Is Not Enough -- Benchmarking Fine-Grained VQA with Web Verification on High-Resolution Real-World Scenes","created":"2026-01-31","cited_by_count":3,"area":"mllm"},{"id":"2605.17829","title":"Interactive Evaluation Requires a Design Science","created":"2026-05-18","cited_by_count":3,"area":null},{"id":"2606.22437","title":"MMGist: A Comprehensive Multimodal Benchmark for 2027","created":"2026-06-21","cited_by_count":3,"area":null},{"id":"2609.09218","title":"The Double Measurement Confound in Agent Benchmarks: De-Scaffolding, Ground-Truth Scoring, and Reliability Beyond the Mean","created":"2026-09-06","cited_by_count":3,"area":"agents"},{"id":"2503.04655","title":"CLDyB: Towards Dynamic Benchmarking for Continual Learning with Pre-trained Models","created":"2025-03-06","cited_by_count":2,"area":null},{"id":"2504.08300","title":"Large Language Models Could Be Rote Learners","created":"2025-04-11","cited_by_count":2,"area":null},{"id":"2504.14039","title":"MEQA: A Meta-Evaluation Framework for Question & Answer LLM Benchmarks","created":"2025-04-18","cited_by_count":2,"area":null},{"id":"2506.00741","title":"Data Swarms: Optimizable Generation of Synthetic Evaluation Data","created":"2025-05-31","cited_by_count":2,"area":null},{"id":"2506.07202","title":"Reasoning Multimodal Large Language Model: Data Contamination and Dynamic Evaluation","created":"2025-06-08","cited_by_count":2,"area":"lr"},{"id":"2510.19005","title":"Dynamic Evaluation for Oversensitivity in LLMs","created":"2025-10-21","cited_by_count":2,"area":null},{"id":"2510.21182","title":"KBE-DME: Dynamic Multimodal Evaluation via Knowledge Enhanced Benchmark Evolution","created":"2025-10-24","cited_by_count":2,"area":"mllm"},{"id":"2511.09139","title":"MACEval: A Multi-Agent Continual Evaluation Network for Large Models","created":"2025-11-12","cited_by_count":2,"area":null},{"id":"2511.10691","title":"Evaluating from Benign to Dynamic Adversarial: A Squid Game for Large Language Models","created":"2025-11-12","cited_by_count":2,"area":null},{"id":"2605.22564","title":"SynAE: A Framework for Measuring the Quality of Synthetic Data for Tool-Calling Agent Evaluations","created":"2026-05-21","cited_by_count":2,"area":"agents"},{"id":"2608.18389","title":"A Jagged Frontier: Evaluating Robustness of Code Agents to Semantics-Preserving Transformations","created":"2026-08-18","cited_by_count":2,"area":"agents"},{"id":"2410.01952","title":"TypedThinker: Diversify Large Language Model Reasoning with Typed Thinking","created":"2024-10-02","cited_by_count":1,"area":"lr"},{"id":"2412.19361","title":"Dynamic Skill Adaptation for Large Language Models","created":"2024-12-26","cited_by_count":1,"area":null},{"id":"2501.13983","title":"AdEval: Alignment-based Dynamic Evaluation to Mitigate Data Contamination in Large Language Models","created":"2025-01-23","cited_by_count":1,"area":null},{"id":"2503.16614","title":"Classification of User Reports for Detection of Faulty Computer Components using NLP Models: A Case Study","created":"2025-03-20","cited_by_count":1,"area":null},{"id":"2510.17868","title":"UniCode: Augmenting Evaluation for Code Reasoning","created":"2025-10-16","cited_by_count":1,"area":"lr"},{"id":"2603.06923","title":"Reforming the Mechanism: Editing Reasoning Patterns in LLMs with Circuit Reshaping","created":"2026-03-06","cited_by_count":1,"area":"lr"},{"id":"2603.11266","title":"The Unlearning Mirage: A Dynamic Framework for Evaluating LLM Unlearning","created":"2026-03-11","cited_by_count":1,"area":"safety"},{"id":"2604.17842","title":"QuickScope: Certifying Hard Questions in Dynamic LLM Benchmarks","created":"2026-04-20","cited_by_count":1,"area":null},{"id":"2604.21916","title":"MathDuels: A Self-Play Benchmark That Grows","created":"2026-04-23","cited_by_count":1,"area":"synth"},{"id":"2609.32248","title":"Anytime-Valid LLM Leaderboards via Benchmark-weighted and Block-Factorized e-Processes","created":"2026-09-26","cited_by_count":1,"area":null},{"id":"2505.16646","title":"SMART: Self-Generating and Self-Validating Multi-Dimensional Assessment for LLMs' Mathematical Problem Solving","created":"2025-05-22","cited_by_count":0,"area":null},{"id":"2512.08965","title":"Financial Instruction Following Evaluation (FIFE)","created":"2025-12-01","cited_by_count":0,"area":null},{"id":"2602.13217","title":"VeRA: Renewing Reasoning Benchmarks with Executable Specifications","created":"2026-01-23","cited_by_count":0,"area":null},{"id":"2603.05290","title":"X-RAY: Mapping LLM Reasoning Capability via Formalized and Calibrated Probes","created":"2026-03-05","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":"2605.18824","title":"Fine-Grained Benchmark Generation for Comprehensive Evaluation of Foundation Models","created":"2026-05-12","cited_by_count":0,"area":null},{"id":"2605.21543","title":"Provable Joint Decontamination for Benchmarking Multiple Large Language Models","created":"2026-05-20","cited_by_count":0,"area":null},{"id":"2605.27914","title":"Does Capability Transfer to Subjective Behavior -- and Would Our Instruments Tell Us? A Self-Evolving, Trust-by-Construction Evaluation Paradigm","created":"2026-05-27","cited_by_count":0,"area":"synth"},{"id":"2605.28882","title":"GrowLoop: Self-Evolving Conversation Evaluation Seeded by Human","created":"2026-05-26","cited_by_count":0,"area":"synth"},{"id":"2605.29339","title":"DMC-CF: Dynamic Multimodal CounterFactual QA benchmark for Causal Reasoning","created":"2026-05-28","cited_by_count":0,"area":"lr"},{"id":"2606.15258","title":"Mask-Proof: An LLM-based Automated Data Curation Pipeline on Mathematical Proofs","created":"2026-06-13","cited_by_count":0,"area":null},{"id":"2607.02141","title":"A$^{2}$utoLPBench: An Auto-Generated, Agent-Friendly LP Benchmark via Inverse-KKT Construction","created":"2026-07-02","cited_by_count":0,"area":"agents"},{"id":"2607.18642","title":"Spaghetti Architect: A Contamination-Resistant, By-Construction-Labelled, Multi-Language Code Dataset Generator","created":"2026-07-21","cited_by_count":0,"area":null},{"id":"2608.04397","title":"NOLLI: A Difficulty-Calibrated Puzzle Benchmark for Diagnosing the English-Korean Performance Gap","created":"2026-08-05","cited_by_count":0,"area":null},{"id":"2608.06933","title":"Ask-E: An Environment for Calibrated Question Generation","created":"2026-08-07","cited_by_count":0,"area":null},{"id":"2608.11047","title":"V-FiLLM: Verified Financial LLM Reasoning Benchmark","created":"2026-08-11","cited_by_count":0,"area":"lr"},{"id":"2608.15979","title":"ALPS: Measuring Valid Creativity in Large Language Models with Mathematical Construction","created":"2026-08-17","cited_by_count":0,"area":null},{"id":"2609.25352","title":"SSP-Bench: A Hybrid Data Generation Framework for Safety, Security, and Privacy Evaluation","created":"2026-09-21","cited_by_count":0,"area":null}],"next_cursor":"100"}