{"total":125,"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":"2508.14704","title":"MCP-Universe: Benchmarking Large Language Models with Real-World Model Context Protocol Servers","created":"2025-08-20","cited_by_count":96,"area":"wm"},{"id":"2507.08794","title":"One Token to Fool LLM-as-a-Judge","created":"2025-07-11","cited_by_count":60,"area":"alignment"},{"id":"2504.10481","title":"xVerify: Efficient Answer Verifier for Reasoning Model Evaluations","created":"2025-04-14","cited_by_count":55,"area":"lr"},{"id":"2504.12328","title":"A Comprehensive Survey of Reward Models: Taxonomy, Applications, Challenges, and Future","created":"2025-04-12","cited_by_count":53,"area":"alignment"},{"id":"2505.17018","title":"SophiaVL-R1: Reinforcing MLLMs Reasoning with Thinking Reward","created":"2025-05-22","cited_by_count":45,"area":"lr"},{"id":"2502.15631","title":"The relationship between reasoning and performance in large language models--o3 (mini) thinks harder, not longer","created":"2025-02-21","cited_by_count":41,"area":"lr"},{"id":"2508.18076","title":"Neither Valid nor Reliable? Investigating the Use of LLMs as Judges","created":"2025-08-25","cited_by_count":39,"area":null},{"id":"2504.03846","title":"Do LLM Evaluators Prefer Themselves for a Reason?","created":"2025-04-04","cited_by_count":38,"area":"lr"},{"id":"2506.02314","title":"ResearchCodeBench: Benchmarking LLMs on Implementing Novel Machine Learning Research Code","created":"2025-06-02","cited_by_count":36,"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":"2506.02592","title":"Beyond the Surface: Measuring Self-Preference in LLM Judgments","created":"2025-06-03","cited_by_count":31,"area":null},{"id":"2505.13975","title":"DRP: Distilled Reasoning Pruning with Skill-aware Step Decomposition for Efficient Large Reasoning Models","created":"2025-05-20","cited_by_count":30,"area":"lr"},{"id":"2505.01976","title":"A Survey on Privacy Risks and Protection in Large Language Models","created":"2025-05-04","cited_by_count":21,"area":"safety"},{"id":"2509.21117","title":"TrustJudge: Inconsistencies of LLM-as-a-Judge and How to Alleviate Them","created":"2025-09-25","cited_by_count":20,"area":null},{"id":"2505.18325","title":"Understanding and Mitigating Overrefusal in LLMs from an Unveiling Perspective of Safety Decision Boundary","created":"2025-05-23","cited_by_count":18,"area":"safety"},{"id":"2601.02430","title":"WebCoderBench: Benchmarking Web Application Generation with Comprehensive and Interpretable Evaluation Metrics","created":"2026-01-05","cited_by_count":18,"area":null},{"id":"2601.20251","title":"Efficient Evaluation of LLM Performance with Statistical Guarantees","created":"2026-01-28","cited_by_count":18,"area":null},{"id":"2505.14279","title":"YESciEval: Robust LLM-as-a-Judge for Scientific Question Answering","created":"2025-05-20","cited_by_count":16,"area":null},{"id":"2503.22688","title":"CodeIF-Bench: Evaluating Instruction-Following Capabilities of Large Language Models in Interactive Code Generation","created":"2025-03-05","cited_by_count":15,"area":null},{"id":"2508.03550","title":"Beyond the Surface: Enhancing LLM-as-a-Judge Alignment with Human via Internal Representations","created":"2025-08-05","cited_by_count":15,"area":"alignment"},{"id":"2505.13772","title":"Krikri: Advancing Open Large Language Models for Greek","created":"2025-05-19","cited_by_count":14,"area":null},{"id":"2505.19504","title":"DOGe: Defensive Output Generation for LLM Protection Against Knowledge Distillation","created":"2025-05-26","cited_by_count":14,"area":"distill"},{"id":"2602.09383","title":"BiasScope: Towards Automated Detection of Bias in LLM-as-a-Judge Evaluation","created":"2026-02-10","cited_by_count":14,"area":null},{"id":"2506.18841","title":"LongWriter-Zero: Mastering Ultra-Long Text Generation via Reinforcement Learning","created":"2025-06-23","cited_by_count":13,"area":null},{"id":"2602.01576","title":"Generative Visual Code Mobile World Models","created":"2026-02-02","cited_by_count":13,"area":"wm"},{"id":"2603.00039","title":"CARE: Confounder-Aware Aggregation for Reliable LLM Evaluation","created":"2026-02-09","cited_by_count":13,"area":null},{"id":"2606.00305","title":"Bridging Reasoning Trajectories in On-Policy Distillation via Near-Future Guidance","created":"2026-05-29","cited_by_count":13,"area":"lr"},{"id":"2504.11101","title":"Consensus Entropy: Harnessing Multi-VLM Agreement for Self-Verifying and Self-Improving OCR","created":"2025-04-15","cited_by_count":12,"area":"mllm"},{"id":"2508.18312","title":"What Matters in Data for DPO?","created":"2025-08-23","cited_by_count":12,"area":"alignment"},{"id":"2505.18659","title":"Adaptive Prediction-Powered AutoEval with Reliability and Efficiency Guarantees","created":"2025-05-24","cited_by_count":11,"area":null},{"id":"2505.19477","title":"Judging with Many Minds: Do More Perspectives Mean Less Prejudice? On Bias Amplifications and Resistance in Multi-Agent Based LLM-as-Judge","created":"2025-05-26","cited_by_count":11,"area":"agents"},{"id":"2604.06996","title":"Self-Preference Bias in Rubric-Based Evaluation of Large Language Models","created":"2026-04-08","cited_by_count":11,"area":null},{"id":"2605.09253","title":"Cornerstones or Stumbling Blocks? Deciphering the Rock Tokens in On-Policy Distillation","created":"2026-05-10","cited_by_count":11,"area":"distill"},{"id":"2502.14854","title":"CLIPPER: Compression enables long-context synthetic data generation","created":"2025-02-20","cited_by_count":10,"area":"synth"},{"id":"2507.11405","title":"DCR: Quantifying Data Contamination in LLMs Evaluation","created":"2025-07-15","cited_by_count":10,"area":null},{"id":"2603.01152","title":"DeepResearch-9K: A Challenging Benchmark Dataset of Deep-Research Agent","created":"2026-03-01","cited_by_count":10,"area":"agents"},{"id":"2604.22891","title":"Quantifying and Mitigating Self-Preference Bias of LLM Judges","created":"2026-04-24","cited_by_count":10,"area":"alignment"},{"id":"2503.04804","title":"What do Large Language Models Say About Animals? Investigating Risks of Animal Harm in Generated Text","created":"2025-03-03","cited_by_count":9,"area":null},{"id":"2505.18759","title":"The Quest for Efficient Reasoning: A Data-Centric Benchmark to CoT Distillation","created":"2025-05-24","cited_by_count":9,"area":"lr"},{"id":"2508.15842","title":"Lexical Hints of Accuracy in LLM Reasoning Chains","created":"2025-08-19","cited_by_count":9,"area":"lr"},{"id":"2509.25154","title":"Who's Your Judge? On the Detectability of LLM-Generated Judgments","created":"2025-09-29","cited_by_count":8,"area":null},{"id":"2504.02902","title":"Beyond Accuracy: The Role of Calibration in Self-Improving Large Language Models","created":"2025-04-03","cited_by_count":7,"area":"synth"},{"id":"2504.10045","title":"CHARM: Calibrating Reward Models With Chatbot Arena Scores","created":"2025-04-14","cited_by_count":7,"area":"alignment"},{"id":"2509.15172","title":"Self-Improvement of Language Models by Post-Training on Multi-Agent Debate","created":"2025-09-18","cited_by_count":7,"area":"agents"},{"id":"2512.05145","title":"Self-Improving VLM Judges Without Human Annotations","created":"2025-12-02","cited_by_count":7,"area":"mllm"},{"id":"2605.17830","title":"Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents","created":"2026-05-18","cited_by_count":7,"area":"agents"},{"id":"2506.02945","title":"Quantitative LLM Judges","created":"2025-06-03","cited_by_count":6,"area":null},{"id":"2604.09563","title":"Seven simple steps for log analysis in AI systems","created":"2026-02-13","cited_by_count":6,"area":null},{"id":"2504.14858","title":"Retrieval is Not Enough: Enhancing RAG Reasoning through Test-Time Critique and Optimization","created":"2025-04-21","cited_by_count":5,"area":"lr"},{"id":"2505.13972","title":"Truth or Twist? Optimal Model Selection for Reliable Label Flipping Evaluation in LLM-based Counterfactuals","created":"2025-05-20","cited_by_count":5,"area":null},{"id":"2507.07419","title":"MedReadCtrl: Personalizing medical text generation with readability-controlled instruction learning","created":"2025-07-10","cited_by_count":5,"area":null},{"id":"2504.14810","title":"DONOD: Efficient and Generalizable Instruction Fine-Tuning for LLMs via Model-Intrinsic Dataset Pruning","created":"2025-04-21","cited_by_count":4,"area":null},{"id":"2511.09833","title":"ACT as Human: Multimodal Large Language Model Data Annotation with Critical Thinking","created":"2025-11-13","cited_by_count":4,"area":"lr"},{"id":"2511.21042","title":"LungNoduleAgent: A Collaborative Multi-Agent System for Precision Diagnosis of Lung Nodules","created":"2025-11-26","cited_by_count":4,"area":null},{"id":"2603.09573","title":"More than the Sum: Panorama-Language Models for Adverse Omni-Scenes","created":"2026-03-10","cited_by_count":4,"area":"mllm"},{"id":"2604.07650","title":"A Statistical Framework for Auditing Behavioral Dependence and Induced Bias in LLM Judges","created":"2026-04-08","cited_by_count":4,"area":null},{"id":"2604.18164","title":"MM-JudgeBias: A Benchmark for Evaluating Compositional Biases in MLLM-as-a-Judge","created":"2026-04-20","cited_by_count":4,"area":"mllm"},{"id":"2605.26156","title":"Turning Bias into Bugs: Bandit-Guided Style Manipulation Attacks on LLM Judges","created":"2026-05-24","cited_by_count":4,"area":null},{"id":"2510.11520","title":"mmWalk: Towards Multi-modal Multi-view Walking Assistance","created":"2025-10-13","cited_by_count":3,"area":null},{"id":"2608.13867","title":"Engineering Reliable Coding Agents: Evaluating and Operating the System Around the Model","created":"2026-08-14","cited_by_count":3,"area":"agents"},{"id":"2609.02246","title":"LLM-as-a-Judge Is Not an Oracle: Why Self-Improving Agents Need Deterministic Guardrails","created":"2026-09-02","cited_by_count":3,"area":"agents"},{"id":"2505.19502","title":"CODE-DITING: A Reasoning-Based Metric for Functional Alignment in Code Evaluation","created":"2025-05-26","cited_by_count":2,"area":"lr"},{"id":"2511.00488","title":"\\texttt{ReMind}: Understanding Deductive Code Reasoning in LLMs","created":"2025-11-01","cited_by_count":2,"area":"lr"},{"id":"2511.08835","title":"Beyond Task-Oriented and Chitchat Dialogues: Proactive and Transition-Aware Conversational Agents","created":"2025-11-11","cited_by_count":2,"area":"agents"},{"id":"2602.13551","title":"Small Reward Models via Backward Inference","created":"2026-02-14","cited_by_count":2,"area":"alignment"},{"id":"2604.04815","title":"LiveFact: A Dynamic, Time-Aware Benchmark for LLM-Driven Fake News Detection","created":"2026-04-06","cited_by_count":2,"area":null},{"id":"2605.31170","title":"Emergent Languages in Populations of Language Model Agents: From Token Efficiency to Oversight Evasion","created":"2026-05-29","cited_by_count":2,"area":"agents"},{"id":"2606.03650","title":"CoEval: Ranking Language Models for Custom Tasks Without Labeled Data or Trustworthy Benchmarks","created":"2026-06-02","cited_by_count":2,"area":null},{"id":"2607.08066","title":"Persuasion Attacks Can Decrease Effectiveness of CoT Monitoring","created":"2026-07-09","cited_by_count":2,"area":"lr"},{"id":"2505.20973","title":"Towards Conversational Development Environments: Using Theory-of-Mind and Multi-Agent Architectures for Requirements Refinement","created":"2025-05-27","cited_by_count":1,"area":"agents"},{"id":"2508.06196","title":"EiCAP: Beyond Fluency, Probing and Improving Emotional Intelligence in LLMs via Psychologically Grounded Multi-Turn Dialogue","created":"2025-08-08","cited_by_count":1,"area":null},{"id":"2509.21170","title":"Fine-Tuning LLMs to Analyze Multiple Dimensions of Code Review: A Maximum Entropy Regulated Long Chain-of-Thought Approach","created":"2025-09-25","cited_by_count":1,"area":"lr"},{"id":"2603.00724","title":"RLAR: An Agentic Reward System for Multi-task Reinforcement Learning on Large Language Models","created":"2026-02-28","cited_by_count":1,"area":"agents"},{"id":"2603.05485","title":"Towards Provably Unbiased LLM Judges via Bias-Bounded Evaluation","created":"2026-03-05","cited_by_count":1,"area":null},{"id":"2603.19266","title":"Probing to Refine: Reinforcement Distillation of LLMs via Explanatory Inversion","created":"2026-02-26","cited_by_count":1,"area":"lr"},{"id":"2604.06711","title":"Specializing Large Models for Oracle Bone Script Interpretation via Component-Grounded Multimodal Knowledge Augmentation","created":"2026-04-08","cited_by_count":1,"area":null},{"id":"2605.20312","title":"Pramana: A Protocol-Layer Treatment of Claim Verification in Autonomous Agent Networks","created":"2026-05-19","cited_by_count":1,"area":"agents"},{"id":"2606.12385","title":"Which Models Are Our Models Built On? Auditing Invisible Dependencies in Modern LLMs","created":"2026-06-10","cited_by_count":1,"area":null},{"id":"2607.02507","title":"What LLM Agents Say When No One Is Watching: Social Structure and Latent Objective Emergence in Multi-Agent Debates","created":"2026-07-02","cited_by_count":1,"area":"agents"},{"id":"2607.05264","title":"SteelBench: Evaluating Vision-Language Models in Real-World Industrial Environments","created":"2026-07-06","cited_by_count":1,"area":"mllm"},{"id":"2608.11434","title":"Benchmarking LLM Judges for Mobile Agent Evaluation","created":"2026-08-11","cited_by_count":1,"area":"agents"},{"id":"2608.25869","title":"Anchoring Bias in LLM-as-a-Judge Systems: Prior Scores Compromise Evaluation Independence","created":"2026-08-26","cited_by_count":1,"area":null},{"id":"2608.26159","title":"Self-Generated Text Recognition: Quality Heuristics, Cross-Task Transfer, and Downstream Bias in LLM Evaluation","created":"2026-07-07","cited_by_count":1,"area":"synth"},{"id":"2609.09647","title":"Black-Box Red Teaming of Agentic AI: A Taxonomy-Driven Framework for Automated Risk Discovery","created":"2026-09-09","cited_by_count":1,"area":"agents"},{"id":"2609.17857","title":"Who Judges Matters: Measuring Family-Conditioned Preference in LLM-as-Judge Panels","created":"2026-09-15","cited_by_count":1,"area":null},{"id":"2610.02293","title":"HakemBench: A Turkish Benchmark of Typed Decisions","created":"2026-10-01","cited_by_count":1,"area":null},{"id":"2505.16036","title":"OpenEthics: A Comprehensive Ethical Evaluation of Open-Source Generative Large Language Models","created":"2025-05-21","cited_by_count":0,"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":"2506.17449","title":"OmniReflect: Discovering Transferable Constitutions for LLM agents via Neuro-Symbolic Reflections","created":"2025-06-20","cited_by_count":0,"area":"agents"},{"id":"2507.19195","title":"Can Small-Scale Data Poisoning Exacerbate Dialect-Linked Biases in Large Language Models?","created":"2025-07-25","cited_by_count":0,"area":"safety"},{"id":"2508.03990","title":"Are Today's LLMs Ready to Explain Well-Being Concepts?","created":"2025-08-06","cited_by_count":0,"area":"alignment"},{"id":"2508.15085","title":"LongRecall: A Structured Approach for Robust Recall Evaluation in Long-Form Text","created":"2025-08-20","cited_by_count":0,"area":null},{"id":"2510.19423","title":"ETOM: A Five-Level Benchmark for Evaluating Tool Orchestration within the MCP Ecosystem","created":"2025-10-22","cited_by_count":0,"area":"agents"},{"id":"2510.25413","title":"Seeing, Signing, and Saying: A Vision-Language Model-Assisted Pipeline for Sign Language Data Acquisition and Curation from Social Media","created":"2025-10-29","cited_by_count":0,"area":"mllm"},{"id":"2510.25884","title":"Approximating Human Preferences Using a Multi-Judge Learned System","created":"2025-10-29","cited_by_count":0,"area":"alignment"},{"id":"2510.27196","title":"MemeArena: Automating Context-Aware Unbiased Evaluation of Harmfulness Understanding for Multimodal Large Language Models","created":"2025-10-31","cited_by_count":0,"area":"mllm"},{"id":"2601.07954","title":"A Human-Centric Pipeline for Aligning Large Language Models with Chinese Medical Ethics","created":"2026-01-12","cited_by_count":0,"area":"alignment"},{"id":"2601.11792","title":"A self-evolving multi-role collaborative framework with fine-grained difficulty guidance for innovative mathematical problem generation","created":"2026-01-16","cited_by_count":0,"area":"synth"},{"id":"2601.17232","title":"Frame-Guided Synthetic Claim Generation for Automatic Fact-Checking Using High-Volume Tabular Data","created":"2026-01-23","cited_by_count":0,"area":null}],"next_cursor":"100"}