{"total":27,"rows":[{"id":"2503.16858","title":"MTBench: A Multimodal Time Series Benchmark for Temporal Reasoning and Question Answering","created":"2025-03-21","cited_by_count":55,"area":"lr"},{"id":"2603.08655","title":"OfficeQA Pro: An Enterprise Benchmark for End-to-End Grounded Reasoning","created":"2026-03-09","cited_by_count":39,"area":"lr"},{"id":"2505.24714","title":"FinMME: Benchmark Dataset for Financial Multi-Modal Reasoning Evaluation","created":"2025-05-30","cited_by_count":30,"area":"lr"},{"id":"2410.04526","title":"FAMMA: A Benchmark for Financial Domain Multilingual Multimodal Question Answering","created":"2024-10-06","cited_by_count":20,"area":"lr"},{"id":"2502.15964","title":"Minions: Cost-efficient Collaboration Between On-device and Cloud Language Models","created":"2025-02-21","cited_by_count":20,"area":"lr"},{"id":"2404.11792","title":"Enhancing Q&A with Domain-Specific Fine-Tuning and Iterative Reasoning: A Comparative Study","created":"2024-04-17","cited_by_count":11,"area":"lr"},{"id":"2411.03314","title":"MME-Finance: A Multimodal Finance Benchmark for Expert-level Understanding and Reasoning","created":"2024-11-05","cited_by_count":7,"area":"lr"},{"id":"2602.05014","title":"DeepRead: Document Structure-Aware Reasoning to Enhance Agentic Search","created":"2026-02-04","cited_by_count":7,"area":"lr"},{"id":"2507.02954","title":"Advanced Financial Reasoning at Scale: A Comprehensive Evaluation of Large Language Models on CFA Level III","created":"2025-06-29","cited_by_count":6,"area":"lr"},{"id":"2503.16856","title":"MMCR: Benchmarking Cross-Source Reasoning in Scientific Papers","created":"2025-03-21","cited_by_count":5,"area":"lr"},{"id":"2603.19225","title":"FinTradeBench: A Financial Reasoning Benchmark for LLMs","created":"2026-03-19","cited_by_count":5,"area":"lr"},{"id":"2608.31075","title":"Scaling Large Reasoning Models beyond Human Supervision: A Path toward Superintelligence","created":"2026-08-31","cited_by_count":5,"area":"lr"},{"id":"2507.18932","title":"MMESGBench: Pioneering Multimodal Understanding and Complex Reasoning Benchmark for ESG Tasks","created":"2025-07-25","cited_by_count":4,"area":"lr"},{"id":"2510.05825","title":"Mitigating Premature Exploitation in Particle-based Monte Carlo for Inference-Time Scaling","created":"2025-10-07","cited_by_count":4,"area":"lr"},{"id":"2606.24526","title":"AGORA: An Archive-Grounded Benchmark for Agentic Workplace Document Reasoning","created":"2026-06-23","cited_by_count":4,"area":"lr"},{"id":"2510.21049","title":"Reasoning's Razor: Reasoning Improves Accuracy but Can Hurt Recall at Critical Operating Points in Safety and Hallucination Detection","created":"2025-10-23","cited_by_count":3,"area":"lr"},{"id":"2511.18177","title":"Rethinking Retrieval: From Traditional Retrieval Augmented Generation to Agentic and Non-Vector Reasoning Systems in the Financial Domain for Large Language Models","created":"2025-11-22","cited_by_count":2,"area":"lr"},{"id":"2510.02906","title":"FinReflectKG -- MultiHop: Financial QA Benchmark for Reasoning with Knowledge Graph Evidence","created":"2025-10-03","cited_by_count":1,"area":"lr"},{"id":"2601.21157","title":"Bridging the Arithmetic Gap: The Cognitive Complexity Benchmark and Financial-PoT for Robust Financial Reasoning","created":"2026-01-29","cited_by_count":1,"area":"lr"},{"id":"2603.08704","title":"Evaluating Financial Intelligence in Large Language Models: Benchmarking SuperInvesting AI with LLM Engines","created":"2026-03-09","cited_by_count":1,"area":"lr"},{"id":"2609.33052","title":"BudgetVerify: Budget-Tiered Verification for Financial QA","created":"2026-09-27","cited_by_count":1,"area":"lr"},{"id":"2601.15297","title":"AfriEconQA: A Benchmark for Quantitative and Temporal Reasoning over World Bank Economic Reports","created":"2026-01-06","cited_by_count":0,"area":"lr"},{"id":"2607.01388","title":"RusFinChain: A Russian Benchmark for Verifiable Chain-of-Thought Reasoning in Finance with Fuzzy-Aligned Evaluation","created":"2026-07-01","cited_by_count":0,"area":"lr"},{"id":"2607.28661","title":"Are the Financial Reasoning from LLMs Credible? A Real World Test over Long-Horizon Statements","created":"2026-07-22","cited_by_count":0,"area":"lr"},{"id":"2608.11047","title":"V-FiLLM: Verified Financial LLM Reasoning Benchmark","created":"2026-08-11","cited_by_count":0,"area":"lr"},{"id":"2608.18534","title":"FinRCA-Bench: Benchmarking Evidence Retrieval and Reasoning for Financial AI Systems","created":"2026-08-19","cited_by_count":0,"area":"lr"},{"id":"2608.27919","title":"From Documents to Reasoning: A Validated Synthetic Data Pipeline and Semantic-Aware Fine-Tuning for Financial Numerical Reasoning","created":"2026-08-28","cited_by_count":0,"area":"lr"}],"next_cursor":null}