{"total":26,"rows":[{"id":"2507.22358","title":"Magentic-UI: Towards Human-in-the-loop Agentic Systems","created":"2025-07-30","cited_by_count":43,"area":"agents"},{"id":"2604.05172","title":"ClawsBench: Evaluating Capability and Safety of LLM Productivity Agents in Simulated Workspaces","created":"2026-04-06","cited_by_count":33,"area":"agents"},{"id":"2605.03596","title":"Workspace-Bench 1.0: Benchmarking AI Agents on Workspace Tasks with Large-Scale File Dependencies","created":"2026-05-05","cited_by_count":29,"area":"agents"},{"id":"2509.10397","title":"RecoWorld: Building Simulated Environments for Agentic Recommender Systems","created":"2025-09-12","cited_by_count":19,"area":"agents"},{"id":"2506.03828","title":"AssetOpsBench: Benchmarking AI Agents for Task Automation in Industrial Asset Operations and Maintenance","created":"2025-06-04","cited_by_count":15,"area":"agents"},{"id":"2603.13594","title":"EnterpriseOps-Gym: Environments and Evaluations for Stateful Agentic Planning and Tool Use in Enterprise Settings","created":"2026-03-13","cited_by_count":15,"area":"agents"},{"id":"2511.09710","title":"Echoing: Identity Failures when LLM Agents Talk to Each Other","created":"2025-11-12","cited_by_count":9,"area":"agents"},{"id":"2509.10769","title":"AgentArch: A Comprehensive Benchmark to Evaluate Agent Architectures in Enterprise","created":"2025-09-13","cited_by_count":8,"area":"agents"},{"id":"2606.12191","title":"Agentic Environment Engineering for Large Language Models: A Survey of Environment Modeling, Synthesis, Evaluation, and Application","created":"2026-06-10","cited_by_count":8,"area":"agents"},{"id":"2509.26506","title":"SCUBA: Salesforce Computer Use Benchmark","created":"2025-09-30","cited_by_count":7,"area":"agents"},{"id":"2606.10749","title":"Toward Secure LLM Agents: Threat Surfaces, Attacks, Defenses, and Evaluation","created":"2026-06-09","cited_by_count":7,"area":"agents"},{"id":"2603.15483","title":"Talk, Evaluate, Diagnose: User-aware Agent Evaluation with Automated Error Analysis","created":"2026-03-16","cited_by_count":6,"area":"agents"},{"id":"2510.25333","title":"CRMWeaver: Building Powerful Business Agent via Agentic RL and Shared Memories","created":"2025-10-29","cited_by_count":5,"area":"agents"},{"id":"2511.17131","title":"UI-CUBE: Enterprise-Grade Computer Use Agent Benchmarking Beyond Task Accuracy to Operational Reliability","created":"2025-11-21","cited_by_count":3,"area":"agents"},{"id":"2608.19741","title":"One Success Isn't Reliability: Thinkingbox, a Sandbox and Benchmark for Agents in Stateful Business Workflows","created":"2026-08-20","cited_by_count":3,"area":"agents"},{"id":"2609.09853","title":"The Era by Eon Benchmark: A Generated Enterprise Estate with Exact Ground Truth for Benchmarking LLM Agents","created":"2026-09-09","cited_by_count":3,"area":"agents"},{"id":"2607.25398","title":"HANDBOOK.md: A Benchmark for Long-Context Agentic Instruction Following","created":"2026-07-28","cited_by_count":2,"area":"agents"},{"id":"2609.04611","title":"$\\tau^\\tau$-Bench: An Environment for End-To-End, Realistic Agent Construction","created":"2026-09-04","cited_by_count":2,"area":"agents"},{"id":"2603.21630","title":"EnterpriseLab: A Full-Stack Platform for developing and deploying agents in Enterprises","created":"2026-03-23","cited_by_count":1,"area":"agents"},{"id":"2609.04667","title":"ERPBench: Evaluating LLM Agents for Enterprise Decision-Making Across Competitive Market Ecologies","created":"2026-09-04","cited_by_count":1,"area":"agents"},{"id":"2609.17885","title":"ERPBench: A State-Grounded Evaluation Paradigm for Computer-Use Agents in Enterprise Software","created":"2026-09-15","cited_by_count":1,"area":"agents"},{"id":"2605.16551","title":"PQR: A Framework to Generate Diverse and Realistic User Queries that Elicit QA Agent Failures","created":"2026-05-15","cited_by_count":0,"area":"agents"},{"id":"2607.22563","title":"Synthetic Scenario Generation for Evaluation of Industry 4.0 Agents","created":"2026-05-29","cited_by_count":0,"area":"agents"},{"id":"2609.28854","title":"Persuaded, Not Informed: Incentive-Misaligned Witnesses Defeat In-Context Grounding","created":"2026-09-23","cited_by_count":0,"area":"agents"},{"id":"2609.30055","title":"Era by Eon: Benchmarking Enterprise Agents on Hidden Knowledge","created":"2026-09-24","cited_by_count":0,"area":"agents"},{"id":"2609.30137","title":"Screen Before You Serve: Simulation for Production Customer Experience AI Agents at 140M Scale","created":"2026-09-24","cited_by_count":0,"area":"agents"}],"next_cursor":null}