{"total":139,"rows":[{"id":"2505.06120","title":"LLMs Get Lost In Multi-Turn Conversation","created":"2025-05-09","cited_by_count":429,"area":null},{"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":"2505.05568","title":"Griffin: Towards a Graph-Centric Relational Database Foundation Model","created":"2025-05-08","cited_by_count":47,"area":null},{"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":"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":"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":"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":"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":"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":"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":"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":"2606.01926","title":"Mitigating Bias in Locally Constrained Decoding via Tractable Proposals","created":"2026-06-01","cited_by_count":8,"area":null},{"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":"2510.26840","title":"SpotIt: Evaluating Text-to-SQL Evaluation with Formal Verification","created":"2025-10-30","cited_by_count":4,"area":null},{"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":"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":"2601.01126","title":"RoboPhD: Self-Improving Text-to-SQL Through Autonomous Agent Evolution","created":"2026-01-03","cited_by_count":3,"area":null},{"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":"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":"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":"2509.23579","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":"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":"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":"2606.31041","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":"2510.16470","title":"Declarative Techniques for NL Queries over Heterogeneous Data","created":"2025-10-18","cited_by_count":1,"area":null},{"id":"2510.27238","title":"DRAMA: Unifying Data Retrieval and Analysis for Open-Domain Analytic Queries","created":"2025-10-31","cited_by_count":1,"area":null},{"id":"2510.27532","title":"SQLSpace: A Representation Space for Text-to-SQL to Discover and Mitigate Robustness Gaps","created":"2025-10-31","cited_by_count":1,"area":null},{"id":"2511.13590","title":"Beyond SELECT: A Comprehensive Taxonomy-Guided Benchmark for Real-World Text-to-SQL Translation","created":"2025-11-17","cited_by_count":1,"area":null},{"id":"2512.16083","title":"Scaling Text2SQL via LLM-efficient Schema Filtering with Functional Dependency Graph Rerankers","created":"2025-12-18","cited_by_count":1,"area":null},{"id":"2512.18779","title":"From Natural Language to Control Signals: A Conceptual Framework for Semantic Channel Finding in Complex Experimental Infrastructure","created":"2025-12-21","cited_by_count":1,"area":null},{"id":"2601.13111","title":"CORE-T: COherent REtrieval of Tables for Text-to-SQL","created":"2026-01-19","cited_by_count":1,"area":null},{"id":"2602.15564","title":"Beyond Static Pipelines: Learning Dynamic Workflows for Text-to-SQL","created":"2026-02-17","cited_by_count":1,"area":null},{"id":"2603.04334","title":"SpotIt+: Verification-based Text-to-SQL Evaluation with Database Constraints","created":"2026-03-04","cited_by_count":1,"area":null},{"id":"2603.05832","title":"Lexara: A User-Centered Toolkit for Evaluating Large Language Models for Conversational Visual Analytics","created":"2026-03-06","cited_by_count":1,"area":null},{"id":"2603.10002","title":"SpreadsheetArena: Decomposing Preference in LLM Generation of Spreadsheet Workbooks","created":"2026-02-16","cited_by_count":1,"area":null},{"id":"2603.12483","title":"Generating Expressive and Customizable Evals for Timeseries Data Analysis Agents with AgentFuel","created":"2026-03-12","cited_by_count":1,"area":null},{"id":"2604.06736","title":"SQLStructEval: Structural Evaluation of LLM Text-to-SQL Generation","created":"2026-04-08","cited_by_count":1,"area":null},{"id":"2604.10667","title":"Learning and Enforcing Context-Sensitive Control for LLMs","created":"2026-04-12","cited_by_count":1,"area":null},{"id":"2604.13201","title":"InfiniteScienceGym: An Unbounded, Procedurally-Generated Benchmark for Scientific Analysis","created":"2026-04-14","cited_by_count":1,"area":null},{"id":"2604.13686","title":"IndicDB -- Benchmarking Multilingual Text-to-SQL Capabilities in Indian Languages","created":"2026-04-15","cited_by_count":1,"area":null},{"id":"2604.25325","title":"R$^3$-SQL: Ranking Reward and Resampling for Text-to-SQL","created":"2026-04-28","cited_by_count":1,"area":null},{"id":"2604.27906","title":"From Unstructured Recall to Schema-Grounded Memory: Reliable AI Memory via Iterative, Schema-Aware Extraction","created":"2026-04-30","cited_by_count":1,"area":null},{"id":"2605.00628","title":"EGREFINE: An Execution-Grounded Optimization Framework for Text-to-SQL Schema Refinement","created":"2026-05-01","cited_by_count":1,"area":null},{"id":"2605.07796","title":"PolySQL: Scaling Text-to-SQL Evaluation Across SQL Dialects via Automated Backend Isomorphism","created":"2026-05-08","cited_by_count":1,"area":null},{"id":"2605.17937","title":"BacktestBench: Benchmarking Large Language Models for Automated Quantitative Strategy Backtesting","created":"2026-05-18","cited_by_count":1,"area":null},{"id":"2605.23595","title":"Learning to Evaluate: Cost-Effective Model Evaluation on Unlabeled Data with Meta-Learning","created":"2026-05-22","cited_by_count":1,"area":null},{"id":"2605.29670","title":"EviLink: Multi-Path Schema Linking with Uncertainty-Guided Evidence Acquisition for Large-Scale Text-to-SQL","created":"2026-05-28","cited_by_count":1,"area":null},{"id":"2606.03363","title":"EntSQL: A Benchmark for Grounding Text-to-SQL in Long-Context Enterprise Knowledge","created":"2026-06-02","cited_by_count":1,"area":null},{"id":"2606.08481","title":"PIPE-Cypher: Automatic Enterprise Benchmark Generation for Text-to-Cypher Systems","created":"2026-06-07","cited_by_count":1,"area":null},{"id":"2606.28387","title":"Schema-First Retrieval: Embedding Catalogs for Natural Language Analytics","created":"2026-06-23","cited_by_count":1,"area":null},{"id":"2607.03991","title":"Knowing When to Stop: Predicting Execution-Consistency Convergence in Text-to-SQL","created":"2026-07-04","cited_by_count":1,"area":null},{"id":"2608.09588","title":"MDB-Link: Hierarchical Schema Linking for Multi-Database Text-to-SQL","created":"2026-08-10","cited_by_count":1,"area":null},{"id":"2608.13926","title":"Never the Number: Structural Abstention for AI Systems Whose Answers Are Consumed as Fact","created":"2026-08-14","cited_by_count":1,"area":null},{"id":"2609.08950","title":"SQLMorph: Query Mutation and Fine-Grained Metrics for Text-to-SQL Evaluation","created":"2026-09-08","cited_by_count":1,"area":null},{"id":"2609.10494","title":"IBIB: A Protocol for Measuring Enterprise AI Systems by Serving Route, Not Model Identifier","created":"2026-09-09","cited_by_count":1,"area":null},{"id":"2503.01804","title":"$\\texttt{SEM-CTRL}$: Semantically Controlled Decoding","created":"2025-03-03","cited_by_count":0,"area":null},{"id":"2505.20591","title":"Effectiveness of Prompt Optimization in NL2SQL Systems","created":"2025-05-26","cited_by_count":0,"area":null},{"id":"2506.23071","title":"Text2VectorSQL: Towards a Unified Interface for Vector Search and SQL Queries","created":"2025-06-29","cited_by_count":0,"area":null},{"id":"2507.17896","title":"VeriMinder: Mitigating Analytical Vulnerabilities in NL2SQL","created":"2025-07-23","cited_by_count":0,"area":null},{"id":"2510.00549","title":"EMR-AGENT: Automating Cohort and Feature Extraction from EMR Databases","created":"2025-10-01","cited_by_count":0,"area":null},{"id":"2510.02394","title":"Retrieval and Augmentation of Domain Knowledge for Text-to-SQL Semantic Parsing","created":"2025-10-01","cited_by_count":0,"area":null},{"id":"2510.18029","title":"DynaQuery: A Self-Adapting Framework for Querying Structured and Multimodal Data","created":"2025-10-20","cited_by_count":0,"area":null},{"id":"2510.24762","title":"Falcon: A Comprehensive Chinese Text-to-SQL Benchmark for Enterprise-Grade Evaluation","created":"2025-10-23","cited_by_count":0,"area":null},{"id":"2512.07926","title":"Can AI autonomously build, operate, and use the entire data stack?","created":"2025-12-08","cited_by_count":0,"area":null},{"id":"2512.21877","title":"CricBench: A Multilingual Benchmark for Evaluating LLMs in Cricket Analytics","created":"2025-12-26","cited_by_count":0,"area":null},{"id":"2512.22744","title":"Bridging Global Intent with Local Details: A Hierarchical Representation Approach for Semantic Validation in Text-to-SQL","created":"2025-12-28","cited_by_count":0,"area":null},{"id":"2601.13695","title":"OptiSQL: Executable SQL Generation from Optical Tokens","created":"2026-01-20","cited_by_count":0,"area":null},{"id":"2601.18119","title":"Beyond Text-to-SQL: Can LLMs Really Debug Enterprise ETL SQL?","created":"2026-01-26","cited_by_count":0,"area":null},{"id":"2602.03633","title":"BIRDTurk: Adaptation of the BIRD Text-to-SQL Dataset to Turkish","created":"2026-02-03","cited_by_count":0,"area":null},{"id":"2602.07086","title":"RAG Strategies for Natural Language-Based SQL Query and REST API Call Generation","created":"2026-02-06","cited_by_count":0,"area":null},{"id":"2603.07449","title":"Dial: A Knowledge-Grounded Dialect-Specific NL2SQL System","created":"2026-03-08","cited_by_count":0,"area":null},{"id":"2603.18447","title":"SODIUM: From Open Web Data to Queryable Databases","created":"2026-03-19","cited_by_count":0,"area":null},{"id":"2604.13048","title":"From Natural Language to PromQL: A Catalog-Driven Framework with Dynamic Temporal Resolution for Cloud-Native Observability","created":"2026-03-15","cited_by_count":0,"area":null},{"id":"2604.20148","title":"Meta-Tool: Efficient Few-Shot Tool Adaptation for Small Language Models","created":"2026-04-22","cited_by_count":0,"area":null},{"id":"2604.21414","title":"SemanticAgent: A Semantics-Aware Framework for Text-to-SQL Data Synthesis","created":"2026-04-23","cited_by_count":0,"area":null},{"id":"2605.05525","title":"Anatomy of a Query: W5H Dimensions and FAR Patterns for Text-to-SQL Evaluation","created":"2026-05-07","cited_by_count":0,"area":null}],"next_cursor":"100"}