{"total":232,"rows":[{"id":"2505.06120","title":"LLMs Get Lost In Multi-Turn Conversation","created":"2025-05-09","cited_by_count":429,"area":null},{"id":"2502.17419","title":"From System 1 to System 2: A Survey of Reasoning Large Language Models","created":"2025-02-24","cited_by_count":320,"area":"lr"},{"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":"2506.13651","title":"xbench: Tracking Agents Productivity Scaling with Profession-Aligned Real-World Evaluations","created":"2025-06-16","cited_by_count":120,"area":null},{"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":"2505.05568","title":"Griffin: Towards a Graph-Centric Relational Database Foundation Model","created":"2025-05-08","cited_by_count":47,"area":null},{"id":"2506.23719","title":"DABstep: Data Agent Benchmark for Multi-step Reasoning","created":"2025-06-30","cited_by_count":46,"area":"lr"},{"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":"2506.06541","title":"KramaBench: A Benchmark for AI Systems on Data-to-Insight Pipelines over Data Lakes","created":"2025-06-06","cited_by_count":33,"area":null},{"id":"2503.18596","title":"LinkAlign: Scalable Schema Linking for Real-World Large-Scale Multi-Database Text-to-SQL","created":"2025-03-24","cited_by_count":29,"area":null},{"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":"2505.04671","title":"Reward-SQL: Boosting Text-to-SQL via Stepwise Execution-Aware Reasoning and Process-Supervised Rewards","created":"2025-05-07","cited_by_count":27,"area":"lr"},{"id":"2509.21016","title":"RL Grokking Recipe: How Does RL Unlock and Transfer New Algorithms in LLMs?","created":"2025-09-25","cited_by_count":23,"area":null},{"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":"2510.17797","title":"Enterprise Deep Research: Steerable Multi-Agent Deep Research for Enterprise Analytics","created":"2025-10-20","cited_by_count":20,"area":null},{"id":"2511.04847","title":"Test-Time Adaptation for LLM Agents via Environment Interaction","created":"2025-11-06","cited_by_count":20,"area":"agents"},{"id":"2510.05318","title":"BIRD-INTERACT: Re-imagining Text-to-SQL Evaluation for Large Language Models via Lens of Dynamic Interactions","created":"2025-10-06","cited_by_count":19,"area":null},{"id":"2411.19504","title":"TQA-Bench: Evaluating LLMs for Multi-Table Question Answering","created":"2024-11-29","cited_by_count":17,"area":null},{"id":"2504.12110","title":"Towards LLM Agents for Earth Observation","created":"2025-04-16","cited_by_count":17,"area":null},{"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":"2506.18951","title":"SWE-SQL: Illuminating LLM Pathways to Solve User SQL Issues in Real-World Applications","created":"2025-06-23","cited_by_count":16,"area":null},{"id":"2504.03598","title":"EnrichIndex: Using LLMs to Enrich Retrieval Indices Offline","created":"2025-04-04","cited_by_count":15,"area":null},{"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":"2504.15077","title":"Think2SQL: Reinforce LLM Reasoning Capabilities for Text2SQL","created":"2025-04-21","cited_by_count":14,"area":"lr"},{"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":"2601.08778","title":"Pervasive Annotation Errors Break Text-to-SQL Benchmarks and Leaderboards","created":"2026-01-13","cited_by_count":13,"area":null},{"id":"2504.09754","title":"Integrating Large Language Models for Automated Structural Analysis","created":"2025-04-13","cited_by_count":12,"area":null},{"id":"2505.17231","title":"ExeSQL: Self-Taught Text-to-SQL Models with Execution-Driven Bootstrapping for SQL Dialects","created":"2025-05-22","cited_by_count":12,"area":"synth"},{"id":"2505.16162","title":"KNN-SSD: Enabling Dynamic Self-Speculative Decoding via Nearest Neighbor Layer Set Optimization","created":"2025-05-22","cited_by_count":11,"area":"inference"},{"id":"2509.25084","title":"Scaling Generalist Data-Analytic Agents","created":"2025-09-29","cited_by_count":11,"area":"agents"},{"id":"2412.05208","title":"A Survey of Large Language Model-Based Generative AI for Text-to-SQL: Benchmarks, Applications, Use Cases, and Challenges","created":"2024-12-06","cited_by_count":10,"area":null},{"id":"2508.00217","title":"Tabular Data Understanding with LLMs: A Survey of Recent Advances and Challenges","created":"2025-07-31","cited_by_count":10,"area":"mllm"},{"id":"2511.21402","title":"Text-to-SQL as Dual-State Reasoning: Integrating Adaptive Context and Progressive Generation","created":"2025-11-26","cited_by_count":10,"area":"lr"},{"id":"2502.12911","title":"Knapsack Optimization-based Schema Linking for LLM-based Text-to-SQL Generation","created":"2025-02-18","cited_by_count":9,"area":null},{"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":"2606.01926","title":"Mitigating Bias in Locally Constrained Decoding via Tractable Proposals","created":"2026-06-01","cited_by_count":8,"area":null},{"id":"2504.05478","title":"GraphRAFT: Retrieval Augmented Fine-Tuning for Knowledge Graphs on Graph Databases","created":"2025-04-07","cited_by_count":7,"area":"lr"},{"id":"2602.13521","title":"Arming Data Agents with Tribal Knowledge","created":"2026-02-13","cited_by_count":7,"area":"agents"},{"id":"2605.18775","title":"Query-Aware Flow Diffusion for Graph-Based RAG with Retrieval Guarantees","created":"2026-04-21","cited_by_count":7,"area":"lr"},{"id":"2604.01608","title":"From Multi-Agent to Single-Agent: When Is Skill Distillation Beneficial?","created":"2026-04-02","cited_by_count":6,"area":null},{"id":"2505.15874","title":"Text-to-Pipeline: Bridging Natural Language and Data Preparation Pipelines","created":"2025-05-21","cited_by_count":5,"area":null},{"id":"2503.05860","title":"Benchmarking AI Models in Software Engineering: A Review, Search Tool, and Unified Approach for Elevating Benchmark Quality","created":"2025-03-07","cited_by_count":4,"area":null},{"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":"2506.13932","title":"Code Reasoning for Software Engineering Tasks: A Survey and A Call to Action","created":"2025-06-16","cited_by_count":4,"area":"lr"},{"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":"2510.26840","title":"SpotIt: Evaluating Text-to-SQL Evaluation with Formal Verification","created":"2025-10-30","cited_by_count":4,"area":null},{"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":"2605.02815","title":"FlexSQL: Flexible Exploration and Execution Make Better Text-to-SQL Agents","created":"2026-05-04","cited_by_count":4,"area":null},{"id":"2606.00547","title":"Learning to Retrieve: Dual-Level Long-Term Memory for Text-to-SQL Agents","created":"2026-05-30","cited_by_count":4,"area":null},{"id":"2607.07026","title":"Constrained Decoding for Diffusion Language Models via Efficient Inference over Finite Automata","created":"2026-07-08","cited_by_count":4,"area":"diffusion"},{"id":"2501.13288","title":"Task-Oriented Automatic Fact-Checking with Frame-Semantics","created":"2025-01-23","cited_by_count":3,"area":null},{"id":"2505.18363","title":"SchemaGraphSQL: Efficient Schema Linking with Pathfinding Graph Algorithms for Text-to-SQL on Large-Scale Databases","created":"2025-05-23","cited_by_count":3,"area":null},{"id":"2507.14372","title":"Text-to-SQL for Enterprise Data Analytics","created":"2025-07-18","cited_by_count":3,"area":null},{"id":"2509.22983","title":"Same Content, Different Representations: A Controlled Study for Table QA","created":"2025-09-26","cited_by_count":3,"area":null},{"id":"2509.23459","title":"MaskSQL: Safeguarding Privacy for LLM-Based Text-to-SQL via Abstraction","created":"2025-09-27","cited_by_count":3,"area":null},{"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":"2601.01126","title":"RoboPhD: Self-Improving Text-to-SQL Through Autonomous Agent Evolution","created":"2026-01-03","cited_by_count":3,"area":null},{"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":"2602.11745","title":"Text2GraphQuery-Bench: A Text to Graph Query Benchmark","created":"2026-02-12","cited_by_count":3,"area":null},{"id":"2602.22223","title":"SQaLe: A Large Text-to-SQL Corpus Grounded in Real Schemas","created":"2025-12-16","cited_by_count":3,"area":null},{"id":"2603.10547","title":"Automatic End-to-End Data Integration using Large Language Models","created":"2026-03-11","cited_by_count":3,"area":null},{"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":"2604.25149","title":"Semantic Layers for Reliable LLM-Powered Data Analytics: A Paired Benchmark of Accuracy and Hallucination Across Three Frontier Models","created":"2026-04-28","cited_by_count":3,"area":null},{"id":"2605.08687","title":"PrepBench: How Far Are We from Natural-Language-Driven Data Preparation?","created":"2026-05-09","cited_by_count":3,"area":null},{"id":"2608.03451","title":"DataSpace: Benchmarking Data Agents for Verifiable Analytics over Heterogeneous Workspaces","created":"2026-08-04","cited_by_count":3,"area":null},{"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":"2502.06759","title":"Rationalization Models for Text-to-SQL","created":"2025-02-10","cited_by_count":2,"area":"lr"},{"id":"2506.07245","title":"SDE-SQL: Enhancing Text-to-SQL Generation in Large Language Models via Self-Driven Exploration with SQL Probes","created":"2025-06-08","cited_by_count":2,"area":null},{"id":"2507.02529","title":"RetrySQL: text-to-SQL training with retry data for self-correcting query generation","created":"2025-07-03","cited_by_count":2,"area":null},{"id":"2508.01222","title":"WebDS: An End-to-End Benchmark for Web-based Data Science","created":"2025-08-02","cited_by_count":2,"area":null},{"id":"2508.17976","title":"Propose and Rectify: A Forensics-Driven MLLM Framework for Image Manipulation Localization","created":"2025-08-25","cited_by_count":2,"area":null},{"id":"2509.04657","title":"Evaluating NL2SQL via SQL2NL","created":"2025-09-04","cited_by_count":2,"area":null},{"id":"2509.07159","title":"PaVeRL-SQL: Text-to-SQL via Partial-Match Rewards and Verbal Reinforcement Learning","created":"2025-09-08","cited_by_count":2,"area":"lr"},{"id":"2509.19508","title":"STARQA: A Question Answering Dataset for Complex Analytical Reasoning over Structured Databases","created":"2025-09-23","cited_by_count":2,"area":"lr"},{"id":"2509.23579","title":"Jackal: A Real-World Execution-Based Benchmark Evaluating Large Language Models on Text-to-JQL Tasks","created":"2025-09-28","cited_by_count":2,"area":null},{"id":"2510.01989","title":"Exploring Database Normalization Effects on SQL Generation","created":"2025-10-02","cited_by_count":2,"area":null},{"id":"2510.13499","title":"ConsintBench: Evaluating Language Models on Real-World Consumer Intent Understanding","created":"2025-10-15","cited_by_count":2,"area":"lr"},{"id":"2510.17491","title":"Empowering Real-World: A Survey on the Technology, Practice, and Evaluation of LLM-driven Industry Agents","created":"2025-10-20","cited_by_count":2,"area":"lr"},{"id":"2510.26495","title":"Rethinking Text-to-SQL: Dynamic Multi-turn SQL Interaction for Real-world Database Exploration","created":"2025-10-30","cited_by_count":2,"area":"lr"},{"id":"2511.03928","title":"SynQuE: Estimating Synthetic Dataset Quality Without Annotations","created":"2025-11-06","cited_by_count":2,"area":"synth"},{"id":"2512.13297","title":"MedInsightBench: Evaluating Medical Analytics Agents Through Multi-Step Insight Discovery in Multimodal Medical Data","created":"2025-12-15","cited_by_count":2,"area":null},{"id":"2512.22364","title":"Cost Trade-offs of Reasoning and Non-Reasoning Large Language Models in Text-to-SQL","created":"2025-12-26","cited_by_count":2,"area":"lr"},{"id":"2601.17942","title":"LLM-Based SQL Generation: Prompting, Self-Refinement, and Adaptive Weighted Majority Voting","created":"2026-01-25","cited_by_count":2,"area":null},{"id":"2602.04101","title":"Interfaze: The Future of AI is built on Task-Specific Small Models","created":"2026-02-04","cited_by_count":2,"area":null},{"id":"2603.07841","title":"An Efficient and Effective Evaluator for Text2SQL Models on Unseen and Unlabeled Data","created":"2026-03-08","cited_by_count":2,"area":null},{"id":"2605.22505","title":"Towards Direct Evaluation of Harness Optimizers via Priority Ranking","created":"2026-05-21","cited_by_count":2,"area":null},{"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":"2606.31041","title":"A Semantic-Layer-Mediated Agent for Natural Language to SQL over Heterogeneous Enterprise Databases","created":"2026-06-30","cited_by_count":2,"area":null},{"id":"2607.06799","title":"What Predicts Correctness in Text-to-SQL? A Selective-Prediction Study","created":"2026-07-07","cited_by_count":2,"area":"lr"},{"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"}],"next_cursor":"100"}