{"total":118,"rows":[{"id":"2306.06070","title":"Mind2Web: Towards a Generalist Agent for the Web","created":"2023-06-09","cited_by_count":1242,"area":"agents"},{"id":"2503.16416","title":"Survey on Evaluation of LLM-based Agents","created":"2025-03-20","cited_by_count":204,"area":"agents"},{"id":"2312.11242","title":"MAC-SQL: A Multi-Agent Collaborative Framework for Text-to-SQL","created":"2023-12-18","cited_by_count":164,"area":"agents"},{"id":"2406.11176","title":"Watch Every Step! LLM Agent Learning via Iterative Step-Level Process Refinement","created":"2024-06-17","cited_by_count":88,"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":"2310.06830","title":"Lemur: Harmonizing Natural Language and Code for Language Agents","created":"2023-10-10","cited_by_count":72,"area":"agents"},{"id":"2603.00729","title":"Qwen3-Coder-Next Technical Report","created":"2026-02-28","cited_by_count":71,"area":"agents"},{"id":"2410.07331","title":"DA-Code: Agent Data Science Code Generation Benchmark for Large Language Models","created":"2024-10-09","cited_by_count":58,"area":"agents"},{"id":"2407.10956","title":"Spider2-V: How Far Are Multimodal Agents From Automating Data Science and Engineering Workflows?","created":"2024-07-15","cited_by_count":56,"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":"2406.08747","title":"StreamBench: Towards Benchmarking Continuous Improvement of Language Agents","created":"2024-06-13","cited_by_count":47,"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":"2502.00675","title":"ReFoRCE: A Text-to-SQL Agent with Self-Refinement, Consensus Enforcement, and Column Exploration","created":"2025-02-02","cited_by_count":37,"area":"agents"},{"id":"2411.04975","title":"SuffixDecoding: Extreme Speculative Decoding for Emerging AI Applications","created":"2024-11-07","cited_by_count":36,"area":"agents"},{"id":"2402.17168","title":"Benchmarking Data Science Agents","created":"2024-02-27","cited_by_count":30,"area":"agents"},{"id":"2604.11978","title":"The Long-Horizon Task Mirage? Diagnosing Where and Why Agentic Systems Break","created":"2026-04-13","cited_by_count":25,"area":"agents"},{"id":"2512.04324","title":"DAComp: Benchmarking Data Agents across the Full Data Intelligence Lifecycle","created":"2025-12-03","cited_by_count":23,"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":"2403.05307","title":"Tapilot-Crossing: Benchmarking and Evolving LLMs Towards Interactive Data Analysis Agents","created":"2024-03-08","cited_by_count":17,"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":"2509.23988","title":"LLM/Agent-as-Data-Analyst: A Survey","created":"2025-09-28","cited_by_count":16,"area":"agents"},{"id":"2607.08124","title":"TTHE: Test-Time Harness Evolution","created":"2026-07-09","cited_by_count":16,"area":"agents"},{"id":"2507.14201","title":"ExCyTIn-Bench: Evaluating LLM agents on Cyber Threat Investigation","created":"2025-07-14","cited_by_count":15,"area":"agents"},{"id":"2511.01008","title":"MARS-SQL: A multi-agent reinforcement learning framework for Text-to-SQL","created":"2025-11-02","cited_by_count":15,"area":"agents"},{"id":"2601.15709","title":"AgentSM: Semantic Memory for Agentic Text-to-SQL","created":"2026-01-22","cited_by_count":14,"area":"agents"},{"id":"2606.01619","title":"ReSkill: Reconciling Skill Creation with Policy Optimization in Agentic RL","created":"2026-06-01","cited_by_count":14,"area":"agents"},{"id":"2406.13408","title":"SQLFixAgent: Towards Semantic-Accurate Text-to-SQL Parsing via Consistency-Enhanced Multi-Agent Collaboration","created":"2024-06-19","cited_by_count":11,"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":"2508.11027","title":"Hell or High Water: Evaluating Agentic Recovery from External Failures","created":"2025-08-14","cited_by_count":9,"area":"agents"},{"id":"2603.10062","title":"Multi-Agent Memory from a Computer Architecture Perspective: Visions and Challenges Ahead","created":"2026-03-09","cited_by_count":9,"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":"2602.16720","title":"APEX-SQL: Talking to the data via Agentic Exploration for Text-to-SQL","created":"2026-02-11","cited_by_count":8,"area":"agents"},{"id":"2402.14851","title":"$R^3$: \"This is My SQL, Are You With Me?\" A Consensus-Based Multi-Agent System for Text-to-SQL Tasks","created":"2024-02-20","cited_by_count":7,"area":"agents"},{"id":"2412.18428","title":"Multi-Modal Data Exploration via Language Agents","created":"2024-12-24","cited_by_count":7,"area":"agents"},{"id":"2508.15809","title":"Chain-of-Query: Unleashing the Power of LLMs in SQL-Aided Table Understanding via Multi-Agent Collaboration","created":"2025-08-14","cited_by_count":6,"area":"agents"},{"id":"2509.00581","title":"SQL-of-Thought: Multi-agentic Text-to-SQL with Guided Error Correction","created":"2025-08-30","cited_by_count":6,"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":"2509.21825","title":"DS-STAR: Data Science Agent for Solving Diverse Tasks across Heterogeneous Formats and Open-Ended Queries","created":"2025-09-26","cited_by_count":6,"area":"agents"},{"id":"2603.16733","title":"IQuest-Coder-V1 Technical Report","created":"2026-03-17","cited_by_count":6,"area":"agents"},{"id":"2608.24358","title":"The Handoff Tax: Continuing Non-Native Trajectories in LLM Agents","created":"2026-08-25","cited_by_count":6,"area":"agents"},{"id":"2510.12831","title":"MTSQL-R1: Towards Long-Horizon Multi-Turn Text-to-SQL via Agentic Training","created":"2025-10-12","cited_by_count":5,"area":"agents"},{"id":"2512.03278","title":"Thucy: An LLM-based Multi-Agent System for Claim Verification across Relational Databases","created":"2025-12-02","cited_by_count":5,"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":"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":"2506.08800","title":"Measuring Data Science Automation: A Survey of Evaluation Tools for AI Assistants and Agents","created":"2025-06-10","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":"2508.17590","title":"RubikSQL: Lifelong Learning Agentic Knowledge Base as an Industrial NL2SQL System","created":"2025-08-25","cited_by_count":4,"area":"agents"},{"id":"2510.03253","title":"Solving the Granularity Mismatch: Hierarchical Preference Learning for Long-Horizon LLM Agents","created":"2025-09-26","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":"2509.01312","title":"TableZoomer: A Collaborative Agent Framework for Large-scale Table Question Answering","created":"2025-09-01","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":"2510.24014","title":"TEXT2DB: Integration-Aware Information Extraction with Large Language Model Agents","created":"2025-10-28","cited_by_count":3,"area":"agents"},{"id":"2601.07880","title":"Sola-Visibility-ISPM: Benchmarking Agentic AI for Identity Security Posture Management Visibility","created":"2026-01-11","cited_by_count":3,"area":"agents"},{"id":"2601.18320","title":"MultiVis-Agent: A Multi-Agent Framework with Logic Rules for Reliable and Comprehensive Cross-Modal Data Visualization","created":"2026-01-26","cited_by_count":3,"area":"agents"},{"id":"2603.16161","title":"SQL-ASTRA: Alleviating Sparse Feedback in Agentic SQL via Column-Set Matching and Trajectory Aggregation","created":"2026-03-17","cited_by_count":3,"area":"agents"},{"id":"2606.14211","title":"Closing the Reflection Gap: A Free Calibration Bonus for Agentic RL","created":"2026-06-12","cited_by_count":3,"area":"agents"},{"id":"2607.07504","title":"Do LLM-Generated Skills Make Better AI Data Scientists? A Component Ablation Across Data-Science Workflows","created":"2026-07-08","cited_by_count":3,"area":"agents"},{"id":"2510.10661","title":"AGENTIQL: An Agent-Inspired Multi-Expert Framework for Text-to-SQL Generation","created":"2025-10-12","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":"2512.11485","title":"Mistake Notebook Learning: Batch-Clustered Failures for Training-Free Agent Adaptation","created":"2025-12-12","cited_by_count":2,"area":"agents"},{"id":"2604.19548","title":"Taming Actor-Observer Asymmetry in Agents via Dialectical Alignment","created":"2026-04-21","cited_by_count":2,"area":"agents"},{"id":"2606.02674","title":"Cross-Vendor Sola ISPM Benchmark: Evaluating Agentic AI for Federated Identity Security Reasoning","created":"2026-06-01","cited_by_count":2,"area":"agents"},{"id":"2609.15779","title":"EvoOntology: A Self-Evolving Ontology Layer for Data Agents","created":"2026-09-14","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":"2505.00989","title":"VTS-LLM: Domain-Adaptive LLM Agent for Enhancing Awareness in Vessel Traffic Services through Natural Language","created":"2025-05-02","cited_by_count":1,"area":"agents"},{"id":"2507.23336","title":"DSBC : Data Science task Benchmarking with Context engineering","created":"2025-07-31","cited_by_count":1,"area":"agents"},{"id":"2509.09234","title":"Agentic LLMs for Question Answering over Tabular Data","created":"2025-09-11","cited_by_count":1,"area":"agents"},{"id":"2509.12612","title":"GBV-SQL: Guided Generation and SQL2Text Back-Translation Validation for Multi-Agent Text2SQL","created":"2025-09-16","cited_by_count":1,"area":"agents"},{"id":"2510.13920","title":"FACTS: Table Summarization via Offline Template Generation with Agentic Workflows","created":"2025-10-15","cited_by_count":1,"area":"agents"},{"id":"2510.14808","title":"Agentic NL2SQL to Reduce Computational Costs","created":"2025-10-16","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":"2602.21480","title":"Both Ends Count! Just How Good are LLM Agents at \"Text-to-Big SQL\"?","created":"2026-02-25","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":"2604.15233","title":"Blue Data Intelligence Layer: Streaming Data and Agents for Multi-source Multi-modal Data-Centric Applications","created":"2026-04-16","cited_by_count":1,"area":"agents"},{"id":"2604.22934","title":"PExA: Parallel Exploration Agent for Complex Text-to-SQL","created":"2026-04-24","cited_by_count":1,"area":"agents"},{"id":"2608.09254","title":"Business Truth, not SQL Accuracy: A Rule-Gated 7B Analytics Agent Outperforms a Direct-Prompted 32B Baseline","created":"2026-08-10","cited_by_count":1,"area":"agents"},{"id":"2608.15389","title":"Agentic-SQL Revisited: Autonomy-Based Taxonomy and Empirical Benchmark Analysis for LLM Text-to-SQL","created":"2026-08-15","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":"2511.04153","title":"BAPPA: Benchmarking Agents, Plans, and Pipelines for Automated Text-to-SQL Generation","created":"2025-11-06","cited_by_count":0,"area":"agents"},{"id":"2511.06455","title":"A Multi-Agent System for Semantic Mapping of Relational Data to Knowledge Graphs","created":"2025-11-09","cited_by_count":0,"area":"agents"},{"id":"2511.11933","title":"InData: Towards Secure Multi-Step, Tool-Based Data Analysis","created":"2025-11-14","cited_by_count":0,"area":"agents"},{"id":"2511.16131","title":"AskDB: An LLM Agent for Natural Language Interaction with Relational Databases","created":"2025-11-20","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":"2601.11687","title":"Semantic Caching and Intent-Driven Context Optimization for Multi-Agent Natural Language to Code Systems","created":"2026-01-16","cited_by_count":0,"area":"agents"},{"id":"2603.17017","title":"LLM NL2SQL Robustness: Surface Noise vs. Linguistic Variation in Traditional and Agentic Settings","created":"2026-03-17","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":"2605.20690","title":"Declarative Data Services: Structured Agentic Discovery for Composing Data Systems","created":"2026-05-20","cited_by_count":0,"area":"agents"},{"id":"2606.05836","title":"ProSPy: A Profiling-Driven SQL-Python Agentic Framework for Enterprise Text-to-SQL","created":"2026-06-04","cited_by_count":0,"area":"agents"},{"id":"2606.13904","title":"SANA: What Matters for QA Agents over Massive Data Lakes?","created":"2026-06-11","cited_by_count":0,"area":"agents"},{"id":"2607.00828","title":"Exploring the Semantic Gap in Agentic Data Systems: A Formative Study of Operationalization Failures in Analytical Workflows","created":"2026-07-01","cited_by_count":0,"area":"agents"},{"id":"2607.19297","title":"Graph-Based Agentic AI with LangGraph: Workflow Pathways for Long-Running Stateful Business Processes","created":"2026-07-21","cited_by_count":0,"area":"agents"},{"id":"2607.22642","title":"CRAFT: Learn the Schema, Execute the Plan","created":"2026-06-24","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":"2608.00485","title":"SERL-SQL: Selective Hindsight Distillation for Text-to-SQL Reinforcement Agentic Learning","created":"2026-08-01","cited_by_count":0,"area":"agents"},{"id":"2608.22063","title":"From SQL Generation to Tool Selection: A Domain-Oriented Pattern for MCP Servers","created":"2026-08-22","cited_by_count":0,"area":"agents"},{"id":"2608.27796","title":"ReToolSQL: Agentic Reinforcement Learning for Robust Text-to-SQL","created":"2026-08-28","cited_by_count":0,"area":"agents"},{"id":"2609.04641","title":"A Cost-Aware Agentic Architecture for NL-to-SQL over Nested Enterprise Schemas, with a New Benchmark","created":"2026-09-04","cited_by_count":0,"area":"agents"}],"next_cursor":"100"}