{"total":34,"rows":[{"id":"2307.13854","title":"WebArena: A Realistic Web Environment for Building Autonomous Agents","created":"2023-07-25","cited_by_count":2006,"area":"agents"},{"id":"2308.03688","title":"AgentBench: Evaluating LLMs as Agents","created":"2023-08-07","cited_by_count":1267,"area":"agents"},{"id":"2401.00812","title":"If LLM Is the Wizard, Then Code Is the Wand: A Survey on How Code Empowers Large Language Models to Serve as Intelligent Agents","created":"2024-01-01","cited_by_count":79,"area":"agents"},{"id":"2402.14672","title":"Middleware for LLMs: Tools Are Instrumental for Language Agents in Complex Environments","created":"2024-02-22","cited_by_count":39,"area":"agents"},{"id":"2407.06423","title":"InsightBench: Evaluating Business Analytics Agents Through Multi-Step Insight Generation","created":"2024-07-08","cited_by_count":32,"area":"agents"},{"id":"2408.07930","title":"MAG-SQL: Multi-Agent Generative Approach with Soft Schema Linking and Iterative Sub-SQL Refinement for Text-to-SQL","created":"2024-08-15","cited_by_count":22,"area":"agents"},{"id":"2504.04808","title":"ELT-Bench: An End-to-End Benchmark for Evaluating AI Agents on ELT Pipelines","created":"2025-04-07","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":"2505.05283","title":"Software Development Life Cycle Perspective: A Survey of Benchmarks for Code Large Language Models and Agents","created":"2025-05-08","cited_by_count":11,"area":"agents"},{"id":"2509.24405","title":"Multilingual Text-to-SQL: Benchmarking the Limits of Language Models with Collaborative Language Agents","created":"2025-09-29","cited_by_count":8,"area":"agents"},{"id":"2509.18710","title":"Autonomous Data Agents: A New Opportunity for Smart Data","created":"2025-09-23","cited_by_count":6,"area":"agents"},{"id":"2408.16991","title":"Tool-Assisted Agent on SQL Inspection and Refinement in Real-World Scenarios","created":"2024-08-30","cited_by_count":4,"area":"agents"},{"id":"2506.11266","title":"Live API-Bench: 2500+ Live APIs for Testing Multi-Step Tool Calling","created":"2025-06-12","cited_by_count":4,"area":"agents"},{"id":"2510.07309","title":"Agent Bain vs. Agent McKinsey: A New Text-to-SQL Benchmark for the Business Domain","created":"2025-10-08","cited_by_count":4,"area":"agents"},{"id":"2503.14251","title":"Towards a Barrier-free GeoQA Portal: Natural Language Interaction with Geospatial Data Using Multi-Agent LLMs and Semantic Search","created":"2025-03-18","cited_by_count":3,"area":"agents"},{"id":"2509.11145","title":"Text2Mem: A Unified Memory Operation Language for Memory Operating System","created":"2025-09-14","cited_by_count":3,"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":"2502.00032","title":"Querying Databases with Function Calling","created":"2025-01-23","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":"2511.03023","title":"PublicAgent: Multi-Agent Design Principles From an LLM-Based Open Data Analysis Framework","created":"2025-11-04","cited_by_count":2,"area":"agents"},{"id":"2307.07255","title":"Dialogue Agents 101: A Beginner's Guide to Critical Ingredients for Designing Effective Conversational Systems","created":"2023-07-14","cited_by_count":1,"area":"agents"},{"id":"2602.01355","title":"Aggregation Queries over Unstructured Text: Benchmark and Agentic Method","created":"2026-02-01","cited_by_count":1,"area":"agents"},{"id":"2602.09642","title":"MATA: Multi-Agent Framework for Reliable and Flexible Table Question Answering","created":"2026-02-10","cited_by_count":1,"area":"agents"},{"id":"2603.03018","title":"REGAL: A Registry-Driven Architecture for Deterministic Grounding of Agentic AI in Enterprise Telemetry","created":"2026-03-03","cited_by_count":1,"area":"agents"},{"id":"2604.07041","title":"AV-SQL: Decomposing Complex Text-to-SQL Queries with Agentic Views","created":"2026-04-08","cited_by_count":1,"area":"agents"},{"id":"2510.14162","title":"FinAI Data Assistant: LLM-based Financial Database Query Processing with the OpenAI Function Calling API","created":"2025-10-15","cited_by_count":0,"area":"agents"},{"id":"2512.18622","title":"A Multi-agent Text2SQL Framework using Small Language Models and Execution Feedback","created":"2025-12-21","cited_by_count":0,"area":"agents"},{"id":"2603.18018","title":"An Agentic System for Schema Aware NL2SQL Generation","created":"2026-02-25","cited_by_count":0,"area":"agents"},{"id":"2604.09470","title":"Agentic Jackal: Live Execution and Semantic Value Grounding for Text-to-JQL","created":"2026-04-10","cited_by_count":0,"area":"agents"},{"id":"2607.28033","title":"DataClawEval: A Benchmark for Data Engineering Agents in Real Industrial Harness","created":"2026-07-30","cited_by_count":0,"area":"agents"},{"id":"2609.16487","title":"Skill-based Agentic Evaluation for Real-time Data Science Tasks","created":"2026-09-15","cited_by_count":0,"area":"agents"},{"id":"2609.21527","title":"OpenMAS-GCom. A Diagnostic Benchmark for Graph-enhanced Multi-Agent Systems","created":"2026-09-18","cited_by_count":0,"area":"agents"},{"id":"2610.04156","title":"Trajectory-Derived Confidence for Reliable, Resource-Aware Clinical Text-to-SQL Agents","created":"2026-10-02","cited_by_count":0,"area":"agents"},{"id":"2610.05540","title":"SALUS: Automated Auditing of NL-to-SQL Benchmarks through Weak Supervision of Multi-Agent Output","created":"2026-10-04","cited_by_count":0,"area":"agents"}],"next_cursor":null}