{"total":14,"rows":[{"id":"2601.09688","title":"DeepResearchEval: An Automated Framework for Deep Research Task Construction and Agentic Evaluation","created":"2026-01-14","cited_by_count":14,"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":"2602.02039","title":"Hunt Instead of Wait: Evaluating Deep Data Research on Large Language Models","created":"2026-02-02","cited_by_count":5,"area":"agents"},{"id":"2607.05174","title":"AgentGym2: Benchmarking Large Language Model Agents in De-Idealized Real-World Environments","created":"2026-07-06","cited_by_count":3,"area":"agents"},{"id":"2606.08661","title":"Data Agents Under Attack: Vulnerabilities in LLM-Driven Analytical Systems","created":"2026-06-07","cited_by_count":2,"area":"agents"},{"id":"2604.12162","title":"AlphaEval: Evaluating Agents in Production","created":"2026-04-14","cited_by_count":1,"area":"agents"},{"id":"2604.25914","title":"DV-World: Benchmarking Data Visualization Agents in Real-World Scenarios","created":"2026-04-28","cited_by_count":1,"area":"agents"},{"id":"2608.17800","title":"StartupBench: Benchmarking General-Purpose Agents on Market-Validated End-to-End Workflows","created":"2026-08-18","cited_by_count":1,"area":"agents"},{"id":"2608.20485","title":"Terminal Agents: A Survey of AI Agents in Command-Line Environments","created":"2026-08-20","cited_by_count":1,"area":"agents"},{"id":"2609.33403","title":"DataMagic: Authoring Data Videos through Declarative Multi-Agent Orchestration","created":"2026-09-27","cited_by_count":1,"area":"agents"},{"id":"2606.19319","title":"Data Intelligence Agents: Interpreting, Modeling, and Querying Enterprise Data via Autonomous Coding Agents","created":"2026-06-17","cited_by_count":0,"area":"agents"},{"id":"2608.17834","title":"AdaLens: Interactive Storyline for Monitoring and Steering Long-Running Agentic Data Analysis","created":"2026-08-18","cited_by_count":0,"area":"agents"},{"id":"2609.34134","title":"StateGuard: Analytical-State Management with Validity-Aware Intervention for Long-Horizon Data Agents","created":"2026-09-28","cited_by_count":0,"area":"agents"},{"id":"2609.35255","title":"Towards Reliable AI Data Scientists: Data Agents with Workflow Harnesses","created":"2026-09-28","cited_by_count":0,"area":"agents"}],"next_cursor":null}