{"total":21,"rows":[{"id":"2509.16941","title":"SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks?","created":"2025-09-21","cited_by_count":279,"area":null},{"id":"2507.15855","title":"Winning Gold at IMO 2025 with a Model-Agnostic Verification-and-Refinement Pipeline","created":"2025-07-21","cited_by_count":82,"area":null},{"id":"2506.05334","title":"Search Arena: Analyzing Search-Augmented LLMs","created":"2025-06-05","cited_by_count":34,"area":null},{"id":"2506.21614","title":"LastingBench: Defend Benchmarks Against Knowledge Leakage","created":"2025-06-21","cited_by_count":14,"area":null},{"id":"2504.21303","title":"Confidence in Large Language Model Evaluation: A Bayesian Approach to Limited-Sample Challenges","created":"2025-04-30","cited_by_count":8,"area":null},{"id":"2507.04491","title":"A validity-guided workflow for robust large language model research in psychology","created":"2025-07-06","cited_by_count":8,"area":null},{"id":"2604.18543","title":"ClawEnvKit: Automatic Environment Generation for Claw-Like Agents","created":"2026-04-20","cited_by_count":8,"area":null},{"id":"2510.20351","title":"When Large Language Models Know the Table: A Framework for Assessing Data Contamination in Tabular Datasets","created":"2025-10-23","cited_by_count":3,"area":null},{"id":"2603.25857","title":"In-Context Molecular Property Prediction with LLMs: A Blinding Study on Memorization and Knowledge Conflicts","created":"2026-03-26","cited_by_count":3,"area":null},{"id":"2601.04895","title":"DVD: A Robust Method for Detecting Variant Contamination in Large Language Model Evaluation","created":"2026-01-08","cited_by_count":1,"area":null},{"id":"2605.24079","title":"TRACER: A Semantic-Aware Framework for Fine-Grained Contamination Detection in Code LLMs","created":"2026-05-22","cited_by_count":1,"area":null},{"id":"2602.08548","title":"How Do Language Models Understand Tables? A Mechanistic Analysis of Cell Location","created":"2026-02-09","cited_by_count":0,"area":null},{"id":"2603.16642","title":"When AI Navigates the Fog of War","created":"2026-03-17","cited_by_count":0,"area":null},{"id":"2603.23514","title":"DepthCharge: A Domain-Agnostic Framework for Measuring Depth-Dependent Knowledge in Large Language Models","created":"2026-03-05","cited_by_count":0,"area":null},{"id":"2604.16392","title":"RoMathExam: A Longitudinal Dataset of Romanian Math Exams (1895-2025) with a Seven-Decade Core (1957-2025)","created":"2026-03-28","cited_by_count":0,"area":null},{"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":"2606.20950","title":"Power Systems Agent Benchmark: Executable Evaluation of AI Agents in Electric Power Engineering","created":"2026-06-18","cited_by_count":0,"area":null},{"id":"2606.30219","title":"EvalSafetyGap: A Hybrid Survey and Conceptual Framework for LLM Evaluation-Safety Failures","created":"2026-06-29","cited_by_count":0,"area":null},{"id":"2609.21888","title":"Detecting Pretraining Data in Large Language Models from a Free-Energy Perspective","created":"2026-09-18","cited_by_count":0,"area":null},{"id":"2609.33411","title":"MetaBench-Harness: Unlocking End-to-End Optimization of Benchmark Harnesses","created":"2026-09-27","cited_by_count":0,"area":null}],"next_cursor":null}