{"total":59,"rows":[{"id":"2502.14499","title":"MLGym: A New Framework and Benchmark for Advancing AI Research Agents","created":"2025-02-20","cited_by_count":124,"area":"agents"},{"id":"2508.07999","title":"WideSearch: Benchmarking Agentic Broad Info-Seeking","created":"2025-08-11","cited_by_count":69,"area":"agents"},{"id":"2602.22769","title":"AMA-Bench: Evaluating Long-Horizon Memory for Agentic Applications","created":"2026-02-26","cited_by_count":53,"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":"2508.11126","title":"AI Agentic Programming: A Survey of Techniques, Challenges, and Opportunities","created":"2025-08-15","cited_by_count":28,"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":"2511.04847","title":"Test-Time Adaptation for LLM Agents via Environment Interaction","created":"2025-11-06","cited_by_count":20,"area":"agents"},{"id":"2510.27287","title":"Can LLMs Help You at Work? A Sandbox for Evaluating LLM Agents in Enterprise Environments","created":"2025-10-31","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":"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":"2603.22862","title":"The Evolution of Tool Use in LLM Agents: From Single-Tool Call to Multi-Tool Orchestration","created":"2026-03-24","cited_by_count":14,"area":"agents"},{"id":"2509.25084","title":"Scaling Generalist Data-Analytic Agents","created":"2025-09-29","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":"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":"2602.13521","title":"Arming Data Agents with Tribal Knowledge","created":"2026-02-13","cited_by_count":7,"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":"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":"2511.17676","title":"LLM and Agent-Driven Data Analysis: A Systematic Approach for Enterprise Applications and System-level Deployment","created":"2025-11-21","cited_by_count":4,"area":"agents"},{"id":"2604.00835","title":"Agentic Tool Use in Large Language Models","created":"2026-04-01","cited_by_count":4,"area":"agents"},{"id":"2511.22884","title":"InsightEval: An Expert-Curated Benchmark for Assessing Insight Discovery in LLM-Driven Data Agents","created":"2025-11-28","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":"2603.20311","title":"kRAIG: A Natural Language-Driven Agent for Automated DataOps Pipeline Generation","created":"2026-03-19","cited_by_count":3,"area":"agents"},{"id":"2603.29399","title":"ELT-Bench-Verified: Benchmark Quality Issues Underestimate AI Agent Capabilities","created":"2026-03-31","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":"2502.00032","title":"Querying Databases with Function Calling","created":"2025-01-23","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":"2607.12790","title":"Who Grades the Grader? Co-Evolving Evaluation Metrics and Skills for Self-Improving LLM Agents","created":"2026-07-14","cited_by_count":2,"area":"agents"},{"id":"2609.05837","title":"AgentBrew: Offline Tool-Use Agent Learning from Raw Real-World Trajectories","created":"2026-09-05","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":"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":"2510.14808","title":"Agentic NL2SQL to Reduce Computational Costs","created":"2025-10-16","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":"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":"2604.22934","title":"PExA: Parallel Exploration Agent for Complex Text-to-SQL","created":"2026-04-24","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":"2608.09254","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":"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":"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":"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":"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":"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":"2606.26627","title":"Agents That Know Too Much: A Data-Centric Survey of Privacy in LLM Agents","created":"2026-06-25","cited_by_count":0,"area":"agents"},{"id":"2607.07397","title":"Agentic Data Environments","created":"2026-07-08","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":"2608.15145","title":"ACTS-SQL: Agentic and Critic-Oriented Tree-Structured SQL Correctness with Large Language Models","created":"2026-08-15","cited_by_count":0,"area":"agents"},{"id":"2609.05776","title":"DI-Bench: Systematically Generating In-Domain Data Intelligence Benchmarks for Enterprise Agents","created":"2026-09-04","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":"2609.19656","title":"Self-Evolving Search Index","created":"2026-09-17","cited_by_count":0,"area":"agents"},{"id":"2609.20886","title":"BI-Agent and BI-Bench: Towards Automating End-to-End Business Intelligence","created":"2026-09-16","cited_by_count":0,"area":"agents"},{"id":"2609.21341","title":"What Stops a Small Language Model From Driving a Database Agent","created":"2026-09-18","cited_by_count":0,"area":"agents"},{"id":"2609.29668","title":"Graph, Loop, and Harness Engineering for Zero-Trust Agentic Data Engineering and Analytical Processing","created":"2026-08-30","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":"2610.02739","title":"Beyond Correctness: Resolving Underspecification in Agentic Text-to-SQL","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}