Fatma Ozcan

Lindsey Linxi Wei, Shreya Shankar, Sepanta Zeighami et al.

One year ago, we open-sourced DocETL, a declarative system for LLM-powered data processing that, as of March 2026, has 3.7K GitHub stars and users across domains (e.g., journalism, law, medicine, policy, finance, and urban planning). In DocETL, users build pipelines by composing operators described in natural language, also known as semantic operators, with an LLM executing each operator's logic. However, due to complexity in the operator or the data it operates on, LLMs often give inaccurate results. To address this challenge, DocETL introduced rewrite directives, or abstract rules that guide LLM agents in rewriting pipelines by decomposing operators or data. For example, decomposing a single filter("is this email sent from an executive and discussing fraud?") into the conjunction of two separate semantic filters may improve accuracy. However, DocETL only optimizes for accuracy, not cost. How do we optimize for both? We present MOAR (Multi-Objective Agentic Rewrites), a new optimizer for DocETL. To target cost optimization, we introduce two new categories of directives and extend all three existing categories with new ones, bringing the total to over 30 directives -- more than doubling what DocETL originally had. Moreover, since operators can interact with each other unpredictably due to LLM behavior, optimizing operators or sub-pipelines individually can yield suboptimal overall plans. Recognizing this, we design a new global search algorithm that explores rewrites in the context of entire pipelines. Since the space of rewrites is infinite -- pipelines can be rewritten in many ways, and each rewritten pipeline can itself be rewritten -- our algorithm adapts a multi-armed bandit framework to prioritize which pipelines to rewrite. Across six workloads, MOAR achieves 27% higher accuracy than ABACUS, the next-best optimizer, while matching its best accuracy at 55% of its cost.

Jiani Zhang, Sercan O. Arik, Cosmin Arad et al.

As LLM-driven autonomous agents evolve to perform complex, multi-step tasks that require integrating multiple datasets, the problem of discovering relevant data sources becomes a key bottleneck. Beyond the challenge posed by the sheer volume of available data sources, data-source selection is difficult because the semantics of data are extremely nuanced and require considering many aspects of the data. To address this, we introduce the Metadata Reasoner, an agentic approach to metadata reasoning, designed to identify a small set of data sources that are both sufficient and minimal for a given analytical task. The Metadata Reasoner leverages a table-search engine to retrieve candidate tables, and then autonomously consults various aspects of the available metadata to determine whether the candidates fit the requirements of the task. We demonstrate the effectiveness of the Metadata Reasoner through a series of empirical studies. Evaluated on the real-world KramaBench datasets for data selection, our approach achieves an average F1-score of 83.16%, outperforming state-of-the-art baselines by a substantial margin of 32 percentage points. Furthermore, evaluations on a newly-created synthetic benchmark based on the BIRD data lake reveal that the Metadata Reasoner is highly robust against redundant and low-quality tables that may be in the data lake. In this noisy environment, it maintains an average of 85.5% F1-score for selecting the right datasets and demonstrates a 99% success rate in avoiding low-quality data.

Jinyang Li, Xiaolong Li, Ge Qu et al.

Resolution of complex SQL issues persists as a significant bottleneck in real-world database applications. Current Large Language Models (LLMs), while adept at text-to-SQL translation, have not been rigorously evaluated on the more challenging task of debugging SQL issues. To address this gap, we introduce BIRD-CRITIC, a new SQL issue debugging benchmark comprising 530 PostgreSQL tasks (BIRD-CRITIC-PG) and 570 multi-dialect tasks (BIRD-CRITIC-Multi), distilled from authentic user issues and replayed within new environments to facilitate rigorous evaluation. Baseline evaluations underscore the task's complexity, with the leading reasoning model O3-Mini achieving only 38.87% success rate on BIRD-CRITIC-PG and 33.33% on BIRD-CRITIC-Multi. Meanwhile, advancing open-source models for database tasks is crucial for empowering local development while safeguarding data privacy. Therefore, we present Six-Gym (Sql-fIX-Gym), a training environment for elevating open-source model capabilities for SQL issue debugging. This environment leverages SQL-Rewind strategy, which automatically generates executable issue-solution datasets by reverse-engineering issues from verified SQLs. However, popular trajectory-based fine-tuning methods do not explore substantial supervisory signals. We further propose f-Plan Boosting, which extracts high-level debugging plans from SQL solutions, enabling teacher LLMs to produce 73.7% more successful trajectories for training. We integrate these components into an open-source agent, Bird-Fixer. Based on Qwen-2.5-Coder-14B, Bird-Fixer achieves 38.11% success rate on BIRD-CRITIC-PG and 29.65% on BIRD-CRITIC-Multi, surpassing leading proprietary models such as Claude-3.7-Sonnet and GPT-4.1, marking a significant step toward democratizing sophisticated SQL-debugging capabilities. The leaderboard and source code are available: https://bird-critic.github.io/

Yeounoh Chung, Gaurav T. Kakkar, Yu Gan et al.

Large Language Models (LLMs) have demonstrated impressive capabilities across a range of natural language processing tasks. In particular, improvements in reasoning abilities and the expansion of context windows have opened new avenues for leveraging these powerful models. NL2SQL is challenging in that the natural language question is inherently ambiguous, while the SQL generation requires a precise understanding of complex data schema and semantics. One approach to this semantic ambiguous problem is to provide more and sufficient contextual information. In this work, we explore the performance and the latency trade-offs of the extended context window (a.k.a., long context) offered by Google's state-of-the-art LLM (\textit{gemini-1.5-pro}). We study the impact of various contextual information, including column example values, question and SQL query pairs, user-provided hints, SQL documentation, and schema. To the best of our knowledge, this is the first work to study how the extended context window and extra contextual information can help NL2SQL generation with respect to both accuracy and latency cost. We show that long context LLMs are robust and do not get lost in the extended contextual information. Additionally, our long-context NL2SQL pipeline based on Google's \textit{gemini-pro-1.5} achieve strong performances on various benchmark datasets without finetuning and expensive self-consistency based techniques.

Nan Huo, Xiaohan Xu, Jinyang Li et al.

Large language models (LLMs) have demonstrated remarkable performance on single-turn text-to-SQL tasks, but real-world database applications predominantly require multi-turn interactions to handle ambiguous queries, execution errors, and evolving user requirements. Existing multi-turn benchmarks fall short by treating conversation histories as static context or limiting evaluation to read-only operations, failing to reflect production-grade database assistant challenges. We introduce BIRD-INTERACT, a benchmark that restores this realism through: (1) a comprehensive interaction environment coupling each database with a hierarchical knowledge base, metadata files, and a function-driven user simulator, enabling models to solicit clarifications, retrieve knowledge, and recover from errors without human supervision; (2) two evaluation settings consisting of a pre-defined conversational protocol (c-Interact) and an open-ended agentic setting (a-Interact) where models autonomously decide when to query the user simulator or explore the environment; (3) a challenging task suite covering the full CRUD spectrum for business-intelligence and operational use cases, guarded by executable test cases. Each task features ambiguous and follow-up sub-tasks requiring dynamic interaction. The suite comprises BIRD-INTERACT-FULL (600 tasks, up to 11,796 interactions) for comprehensive performance assessment, and BIRD-INTERACT-LITE (300 tasks with simplified databases) for detailed behavioral analysis and rapid method development. Our empirical results highlight BIRD-INTERACT's difficulty: GPT-5 completes only 8.67% of tasks in c-Interact and 17.00% in a-Interact. Analysis via memory grafting and Interaction Test-time Scaling validates the importance of effective interaction for complex, dynamic text-to-SQL tasks.

Zixuan Yi, Sami Abu-el-Haija, Yawen Wang et al.

DB engines produce efficient query execution plans by relying on cost models. Practical implementations estimate cardinality of queries using heuristics, with magic numbers tuned to improve average performance on benchmarks. Empirically, estimation error significantly grows with query complexity. Alternatively, learning-based estimators offer improved accuracy, but add operational complexity preventing their adoption in-practice. Recognizing that query workloads contain highly repetitive subquery patterns, we learn many simple regressors online, each localized to a pattern. The regressor corresponding to a pattern can be randomly-accessed using hash of graph structure of the subquery. Our method has negligible overhead and competes with SoTA learning-based approaches on error metrics. Further, amending PostgreSQL with our method achieves notable accuracy and runtime improvements over traditional methods and drastically reduces operational costs compared to other learned cardinality estimators, thereby offering the most practical and efficient solution on the Pareto frontier. Concretely, simulating JOB-lite workload on IMDb speeds-up execution by 7.5 minutes (>30%) while incurring only 37 seconds overhead for online learning.

Shivasankari Kannan, Yeounoh Chung, Amita Gondi et al.

The demand for high-fidelity test data is paramount in industrial settings where access to production data is largely restricted. Traditional data generation methods often fall short, struggling with low-fidelity and the ability to model complex data structures and semantic relationships that are critical for testing complex SQL code generation services like Natural Language to SQL (NL2SQL). In this paper, we address the critical need for generating syntactically correct and semantically relevant high-fidelity mock data for complex data structures that includes columns with nested structures that we frequently encounter in Google workloads. We highlight the limitations of existing approaches used in production, particularly their inability to handle large and complex data structures, as well as the lack of semantically coherent test data that lead to limited test coverage. We demonstrate that by leveraging Large Language Models (LLMs) and incorporating strategic pre- and post-processing steps, we can generate syntactically correct and semantically relevant high-fidelity test data that adheres to complex structural constraints and maintains semantic integrity to the SQL test targets (queries/functions). This approach supports comprehensive testing of complex SQL queries involving joins, aggregations, and even deeply nested subqueries, ensuring robust evaluation of SQL code generation services, like NL2SQL and SQL Code Assistant. Our results demonstrate the practical utility of an LLM (\textit{gemini}) based test data generation for industrial SQL code generation services where generating high-fidelity test data is essential due to the frequent unavailability and inaccessibility of production datasets for testing.

Venkata Vamsikrishna Meduri, Abdul Quamar, Chuan Lei et al.

Conversational interfaces to Business Intelligence (BI) applications enable data analysis using a natural language dialog in small incremental steps. To truly unleash the power of conversational BI to democratize access to data, a system needs to provide effective and continuous support for data analysis. In this paper, we propose BI-REC, a conversational recommendation system for BI applications to help users accomplish their data analysis tasks. We define the space of data analysis in terms of BI patterns, augmented with rich semantic information extracted from the OLAP cube definition, and use graph embeddings learned using GraphSAGE to create a compact representation of the analysis state. We propose a two-step approach to explore the search space for useful BI pattern recommendations. In the first step, we train a multi-class classifier using prior query logs to predict the next high-level actions in terms of a BI operation (e.g., {\em Drill-Down} or {\em Roll-up}) and a measure that the user is interested in. In the second step, the high-level actions are further refined into actual BI pattern recommendations using collaborative filtering. This two-step approach allows us to not only divide and conquer the huge search space, but also requires less training data. Our experimental evaluation shows that BI-REC achieves an accuracy of 83% for BI pattern recommendations and up to 2X speedup in latency of prediction compared to a state-of-the-art baseline. Our user study further shows that BI-REC provides recommendations with a precision@3 of 91.90% across several different analysis tasks.