{"total":18,"rows":[{"id":"2308.03688","title":"AgentBench: Evaluating LLMs as Agents","created":"2023-08-07","cited_by_count":1267,"area":"agents"},{"id":"2510.16872","title":"DeepAnalyze: Agentic Large Language Models for Autonomous Data Science","created":"2025-10-19","cited_by_count":50,"area":"agents"},{"id":"2510.23587","title":"A Survey of Data Agents: Emerging Paradigm or Overstated Hype?","created":"2025-10-27","cited_by_count":30,"area":"agents"},{"id":"2402.17896","title":"Researchy Questions: A Dataset of Multi-Perspective, Decompositional Questions for LLM Web Agents","created":"2024-02-27","cited_by_count":23,"area":"agents"},{"id":"2406.00252","title":"Towards Rationality in Language and Multimodal Agents: A Survey","created":"2024-06-01","cited_by_count":16,"area":"agents"},{"id":"2402.11534","title":"PreAct: Prediction Enhances Agent's Planning Ability","created":"2024-02-18","cited_by_count":12,"area":"agents"},{"id":"2606.29955","title":"SpreadsheetBench 2: Evaluating Agents on End-to-End Business Spreadsheet Workflows","created":"2026-06-29","cited_by_count":11,"area":"agents"},{"id":"2602.04634","title":"WideSeek-R1: Exploring Width Scaling for Broad Information Seeking via Multi-Agent Reinforcement Learning","created":"2026-02-04","cited_by_count":9,"area":"agents"},{"id":"2507.16725","title":"RAVine: Reality-Aligned Evaluation for Agentic Search","created":"2025-07-22","cited_by_count":6,"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":"2409.18538","title":"A Survey on Complex Tasks for Goal-Directed Interactive Agents","created":"2024-09-27","cited_by_count":2,"area":"agents"},{"id":"2507.10281","title":"Toward Real-World Table Agents: Capabilities, Workflows, and Design Principles for LLM-based Table Intelligence","created":"2025-07-14","cited_by_count":2,"area":"agents"},{"id":"2604.22861","title":"IntrAgent: An LLM Agent for Content-Grounded Information Retrieval through Literature Review","created":"2026-04-23","cited_by_count":2,"area":"agents"},{"id":"2608.03735","title":"An Actionable Diagnosis of Multilingual, Multi-Agent Planning Failures","created":"2026-08-04","cited_by_count":1,"area":"agents"},{"id":"2603.14229","title":"Agentic DAG-Orchestrated Planner Framework for Multi-Modal, Multi-Hop Question Answering in Hybrid Data Lakes","created":"2026-03-15","cited_by_count":0,"area":"agents"},{"id":"2606.27595","title":"Ko-WideSearch: A Korean Breadth-Search Benchmark for Exhaustive Set Enumeration by Web Agents","created":"2026-06-25","cited_by_count":0,"area":"agents"},{"id":"2607.27726","title":"Baikal: Structured Search for Deep Research over Data Lakes","created":"2026-07-30","cited_by_count":0,"area":"agents"},{"id":"2609.34157","title":"TableSeek: Structure-Preserving Agentic Evidence Seeking over Heterogeneous Table Corpora","created":"2026-09-28","cited_by_count":0,"area":"agents"}],"next_cursor":null}