{"total":16,"rows":[{"id":"2512.13168","title":"Finch: Benchmarking Finance & Accounting across Spreadsheet-Centric Enterprise Workflows","created":"2025-12-15","cited_by_count":10,"area":null},{"id":"2603.01203","title":"How Well Does Agent Development Reflect Real-World Work?","created":"2026-03-01","cited_by_count":10,"area":null},{"id":"2604.04901","title":"FileGram: Grounding Agent Personalization in File-System Behavioral Traces","created":"2026-04-06","cited_by_count":3,"area":null},{"id":"2605.13880","title":"PREPING: Zero-Task Agent Memory Construction via Self-Practice","created":"2026-05-11","cited_by_count":3,"area":null},{"id":"2603.04857","title":"FireBench: Evaluating Instruction Following in Enterprise and API-Driven LLM Applications","created":"2026-03-05","cited_by_count":2,"area":null},{"id":"2507.15501","title":"ASPERA: A Simulated Environment to Evaluate Planning for Complex Action Execution","created":"2025-07-21","cited_by_count":1,"area":null},{"id":"2512.03560","title":"Reason-Plan-ReAct: A Reasoner-Planner Supervising a ReAct Executor for Complex Enterprise Tasks","created":"2025-12-03","cited_by_count":1,"area":null},{"id":"2603.14730","title":"GNNVerifier: Graph-based Verifier for LLM Task Planning","created":"2026-03-16","cited_by_count":1,"area":null},{"id":"2607.19865","title":"DocOps: A Verifiable Benchmark for Autonomous Agents in Complex Document Operations","created":"2026-07-22","cited_by_count":1,"area":null},{"id":"2608.10366","title":"DSAgentBench: Can Agents Automate End-to-End Data-Science Workflows in Real Computer Environments?","created":"2026-08-11","cited_by_count":1,"area":null},{"id":"2512.04445","title":"Automating Complex Document Workflows via Stepwise and Rollback-Enabled Operation Orchestration","created":"2025-12-04","cited_by_count":0,"area":null},{"id":"2606.10956","title":"Mind the Gap: Can Frontier LLMs Pass a Standardized Office Proficiency Exam?","created":"2026-06-09","cited_by_count":0,"area":null},{"id":"2606.18191","title":"DRFLOW: A Deep Research Benchmark for Personalized Workflow Prediction","created":"2026-06-16","cited_by_count":0,"area":null},{"id":"2607.01245","title":"Office Comprehension Benchmark","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2609.07784","title":"xDailyBench: Benchmarking LLMs on Professional Consultation for Real-Life Problems","created":"2026-09-07","cited_by_count":0,"area":null},{"id":"2609.34469","title":"The Last Mile Is the File: OfficeEditBench for Preservation-Aware Office Editing","created":"2026-09-28","cited_by_count":0,"area":null}],"next_cursor":null}