{"total":26,"rows":[{"id":"2501.12380","title":"MMVU: Measuring Expert-Level Multi-Discipline Video Understanding","created":"2025-01-21","cited_by_count":137,"area":null},{"id":"2503.18102","title":"AgentRxiv: Towards Collaborative Autonomous Research","created":"2025-03-23","cited_by_count":72,"area":null},{"id":"2511.11562","title":"PRBench: Large-Scale Expert Rubrics for Evaluating High-Stakes Professional Reasoning","created":"2025-11-14","cited_by_count":32,"area":null},{"id":"2411.05764","title":"FinDVer: Explainable Claim Verification over Long and Hybrid-Content Financial Documents","created":"2024-11-08","cited_by_count":19,"area":null},{"id":"2503.04644","title":"IFIR: A Comprehensive Benchmark for Evaluating Instruction-Following in Expert-Domain Information Retrieval","created":"2025-03-06","cited_by_count":16,"area":null},{"id":"2410.15580","title":"Language Models are Symbolic Learners in Arithmetic","created":"2024-10-21","cited_by_count":11,"area":null},{"id":"2412.11757","title":"SCITAT: A Question Answering Benchmark for Scientific Tables and Text Covering Diverse Reasoning Types","created":"2024-12-16","cited_by_count":10,"area":null},{"id":"2510.15232","title":"FinTrust: A Comprehensive Benchmark of Trustworthiness Evaluation in Finance Domain","created":"2025-10-17","cited_by_count":8,"area":null},{"id":"2506.08762","title":"EDINET-Bench: Evaluating LLMs on Complex Financial Tasks using Japanese Financial Statements","created":"2025-06-10","cited_by_count":6,"area":null},{"id":"2509.18776","title":"AECBench: A Hierarchical Benchmark for Knowledge Evaluation of Large Language Models in the AEC Field","created":"2025-09-23","cited_by_count":6,"area":null},{"id":"2604.05912","title":"FrontierFinance: A Long-Horizon Computer-Use Benchmark of Real-World Financial Tasks","created":"2026-04-07","cited_by_count":3,"area":null},{"id":"2606.15949","title":"FinBalance: A Multi-Document Accounting Reconciliation Benchmark","created":"2026-06-14","cited_by_count":3,"area":null},{"id":"2502.17253","title":"MULTITAT: Benchmarking Multilingual Table-and-Text Question Answering","created":"2025-02-24","cited_by_count":2,"area":null},{"id":"2602.10886","title":"The CLEF-2026 FinMMEval Lab: Multilingual and Multimodal Evaluation of Financial AI Systems","created":"2026-02-11","cited_by_count":2,"area":null},{"id":"2510.00156","title":"AuditAgent: Expert-Guided Multi-Agent Reasoning for Cross-Document Fraudulent Evidence Discovery","created":"2025-09-30","cited_by_count":1,"area":null},{"id":"2412.09280","title":"Learning to Solve Domain-Specific Calculation Problems with Knowledge-Intensive Programs Generator","created":"2024-12-12","cited_by_count":0,"area":null},{"id":"2412.09884","title":"Benchmarking Table Comprehension In The Wild","created":"2024-12-13","cited_by_count":0,"area":null},{"id":"2506.07315","title":"Towards Competent AI for Fundamental Analysis in Finance: A Benchmark Dataset and Evaluation","created":"2025-05-22","cited_by_count":0,"area":null},{"id":"2601.06401","title":"BizFinBench.v2: Towards Reliable LLMs in Finance via Real-User Data and Offline/Online Bilingual Evaluation","created":"2026-01-10","cited_by_count":0,"area":null},{"id":"2605.13330","title":"FIND: Toward Multimodal Financial Reasoning and Question Answering for Indic Languages","created":"2026-05-13","cited_by_count":0,"area":null},{"id":"2605.29586","title":"FinVerBench: Benchmark Validity and Calibration in Large Language Model Financial Statement Verification","created":"2026-05-28","cited_by_count":0,"area":null},{"id":"2606.11537","title":"MoCA-Agent: A Market-of-Claims Code Agent for Financial and Numerical Reasoning","created":"2026-06-10","cited_by_count":0,"area":null},{"id":"2608.28155","title":"FinExam-10K: When Retrieval Helps Financial Reasoning?","created":"2026-08-28","cited_by_count":0,"area":null},{"id":"2609.01386","title":"When Tokenization is Secretly Output Supervision","created":"2026-09-01","cited_by_count":0,"area":null},{"id":"2609.07603","title":"FinCUABuild: Can Agents Build Reliable Benchmarks for Dynamic Financial Computer Use?","created":"2026-09-07","cited_by_count":0,"area":null},{"id":"2610.03564","title":"Knowledge or Calculator? Decomposing the Skill Premium in Verifiable Financial Agent Workflows","created":"2026-10-02","cited_by_count":0,"area":null}],"next_cursor":null}