{"total":18,"rows":[{"id":"2511.20766","title":"OpenApps: Simulating Environment Variations to Measure UI-Agent Reliability","created":"2025-11-25","cited_by_count":12,"area":null},{"id":"2606.14502","title":"From Chatbot to Digital Colleague: The Paradigm Shift Toward Persistent Autonomous AI","created":"2026-06-12","cited_by_count":6,"area":null},{"id":"2606.14832","title":"PhoneHarness: Harnessing Phone-Use Agents through Mixed GUI, CLI, and Tool Actions","created":"2026-06-12","cited_by_count":6,"area":null},{"id":"2604.10988","title":"WebForge: Breaking the Realism-Reproducibility-Scalability Trilemma in Browser Agent Benchmark","created":"2026-04-13","cited_by_count":5,"area":null},{"id":"2604.06111","title":"AgentCE-Bench: Agent Configurable Evaluation with Scalable Horizons and Controllable Difficulty under Lightweight Environments","created":"2026-04-07","cited_by_count":3,"area":null},{"id":"2608.27391","title":"CorporateBench: Large-Scale Q&A Benchmarking with Temporal Knowledge Bases","created":"2026-08-27","cited_by_count":1,"area":null},{"id":"2609.35732","title":"Failure-Transparent Agents: Benchmarking Post-Failure Reporting in Tool-Using Language Models","created":"2026-09-28","cited_by_count":1,"area":null},{"id":"2503.21544","title":"SWI: Speaking with Intent in Large Language Models","created":"2025-03-27","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":"2608.15931","title":"PLSQLBench: Benchmarking LLM Systems for Executable Procedural Database Programming","created":"2026-08-16","cited_by_count":0,"area":null},{"id":"2608.23200","title":"LongWoF-Bench: Evaluating EvoMap Genes for Verifiable Long-Workflow Tasks","created":"2026-08-24","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":"2609.12366","title":"ORQA: An Occupation-Realistic Question and Answer Framework for LLM Professional Knowledge","created":"2026-09-11","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},{"id":"2610.04906","title":"Scaling Verifiable Environments for Long-horizon Work Agents","created":"2026-10-04","cited_by_count":0,"area":null},{"id":"2610.13623","title":"APEX-Harm: Evaluating Agent Safety in Shared Professional Workspaces","created":"2026-10-09","cited_by_count":0,"area":null},{"id":"2610.16397","title":"Recursive Environment Scaling for General Long-Horizon Agents","created":"2026-10-12","cited_by_count":0,"area":null},{"id":"2610.18603","title":"AgentStripes: An Evidence-Graded Maturity Model for AI Agents","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}