{"total":19,"rows":[{"id":"2606.05661","title":"Continual Learning Bench: Evaluating Frontier AI Systems in Real-World Stateful Environments","created":"2026-06-04","cited_by_count":17,"area":null},{"id":"2602.11685","title":"DRACO: a Cross-Domain Benchmark for Deep Research Accuracy, Completeness, and Objectivity","created":"2026-02-12","cited_by_count":14,"area":null},{"id":"2512.13168","title":"Finch: Benchmarking Finance & Accounting across Spreadsheet-Centric Enterprise Workflows","created":"2025-12-15","cited_by_count":10,"area":null},{"id":"2606.02859","title":"Economy of Minds: Emerging Multi-Agent Intelligence with Economic Interactions","created":"2026-06-01","cited_by_count":5,"area":null},{"id":"2603.04403","title":"FinRetrieval: A Benchmark for Financial Data Retrieval by AI Agents","created":"2026-01-02","cited_by_count":4,"area":null},{"id":"2604.15151","title":"QuantCode-Bench: A Benchmark for Evaluating the Ability of Large Language Models to Generate Executable Algorithmic Trading Strategies","created":"2026-04-16","cited_by_count":4,"area":null},{"id":"2608.06144","title":"FinEvo-Bench: A Longitudinal Benchmark for Self-Evolving Agents in Professional Financial Workflows","created":"2026-08-06","cited_by_count":3,"area":null},{"id":"2608.27147","title":"Thomson: Continual Learning of Frontier Models for SovereignAI","created":"2026-08-27","cited_by_count":2,"area":null},{"id":"2604.22436","title":"AgentSearchBench: A Benchmark for AI Agent Search in the Wild","created":"2026-04-24","cited_by_count":1,"area":null},{"id":"2606.03918","title":"Hedge-Bench: Benchmarking Agents on Hard, Realistic Tasks Pertaining to Financial Reasoning","created":"2026-06-02","cited_by_count":1,"area":null},{"id":"2608.01204","title":"ShiJianBench: From Dialogue to Decision for Long-Horizon Evaluation of Investment Advisors","created":"2026-08-02","cited_by_count":1,"area":null},{"id":"2608.14747","title":"WANDR: A Benchmark for Wide and Deep Research","created":"2026-08-14","cited_by_count":1,"area":null},{"id":"2512.14717","title":"Is GPT-OSS All You Need? Benchmarking Large Language Models for Financial Intelligence and the Surprising Efficiency Paradox","created":"2025-12-09","cited_by_count":0,"area":null},{"id":"2606.11166","title":"Flaws in the LLM Automation Narrative","created":"2026-06-09","cited_by_count":0,"area":null},{"id":"2607.25656","title":"OrchBench: Evaluating Multi-Agent Orchestration Plans in Isolation via Deterministic Simulation","created":"2026-07-28","cited_by_count":0,"area":null},{"id":"2607.25891","title":"Messier: A High-Resolution Corpus for Cross-Benchmark Agent Evaluation","created":"2026-07-28","cited_by_count":0,"area":null},{"id":"2608.25325","title":"FinRiskAtlas: Decision-Aligned Evaluation of Large Language Models for Financial Risk Review","created":"2026-08-26","cited_by_count":0,"area":null},{"id":"2609.35744","title":"FinAutoRubric: Expert-Guided Automatic Rubric Generation for Evaluating Financial Research Agents","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2610.01306","title":"DAYJOB: A Benchmark for Long-Horizon Professional Work","created":"2026-10-01","cited_by_count":0,"area":null}],"next_cursor":null}