arXiv subjects

Eser Kandogan

Publications and source records attributed to Eser Kandogan.

14 recordsLinked to original sources

arXiv2026

Exploring the Semantic Gap in Agentic Data Systems: A Formative Study of Operationalization Failures in Analytical Workflows

Large language models (LLMs) are increasingly used to generate queries, invoke tools, and construct analytical workflows. Although recent advances have substantially improved workflow generation and execution, the semantic information required to operationalize analytical concepts often lies beyond what is explicitly represented in database schemas and data values. We present a cross-domain formative study of operationalization failures in agent-generated analytical workflows. Across 236 analytical intents spanning finance, human resources, and public safety domains, we identify 153 recurring failures despite successful workflow generation and execution. Our analysis reveals five recurring classes of failures: comparative grounding, process reasoning, quantitative reasoning, role confusion, and policy grounding. These findings suggest a semantic gap between user-level analytical concepts and the information available to workflow-generation systems. More broadly, they raise questions about the admissibility of analytical operations and suggest that future agentic data systems may require richer semantic representations to bridge the gap between analytical intent and executable computation.

cs.DB↗

arXiv2026

Blue Data Intelligence Layer: Streaming Data and Agents for Multi-source Multi-modal Data-Centric Applications

NL2SQL systems aim to address the growing need for natural language interaction with data. However, real-world information rarely maps to a single SQL query because (1) users express queries iteratively (2) questions often span multiple data sources beyond the closed-world assumption of a single database, and (3) queries frequently rely on commonsense or external knowledge. Consequently, satisfying realistic data needs require integrating heterogeneous sources, modalities, and contextual data. In this paper, we present Blue's Data Intelligence Layer (DIL) designed to support multi-source, multi-modal, and data-centric applications. Blue is a compound AI system that orchestrates agents and data for enterprise settings. DIL serves as the data intelligence layer for agentic data processing, to bridge the semantic gap between user intent and available information by unifying structured enterprise data, world knowledge accessible through LLMs, and personal context obtained through interaction. At the core of DIL is a data registry that stores metadata for diverse data sources and modalities to enable both native and natural language queries. DIL treats LLMs, the Web, and the User as source 'databases', each with their own query interface, elevating them to first-class data sources. DIL relies on data planners to transform user queries into executable query plans. These plans are declarative abstractions that unify relational operators with other operators spanning multiple modalities. DIL planners support decomposition of complex requests into subqueries, retrieval from diverse sources, and finally reasoning and integration to produce final results. We demonstrate DIL through two interactive scenarios in which user queries dynamically trigger multi-source retrieval, cross-modal reasoning, and result synthesis, illustrating how compound AI systems can move beyond single database NL2SQL.

cs.AI↗

arXiv2025

Effectiveness of Prompt Optimization in NL2SQL Systems

NL2SQL approaches have greatly benefited from the impressive capabilities of large language models (LLMs). In particular, bootstrapping an NL2SQL system for a specific domain can be as simple as instructing an LLM with sufficient contextual information, such as schema details and translation demonstrations. However, building an accurate system still requires the rigorous task of selecting the right context for each query-including identifying relevant schema elements, cell values, and suitable exemplars that help the LLM understand domain-specific nuances. Retrieval-based methods have become the go-to approach for identifying such context. While effective, these methods introduce additional inference-time costs due to the retrieval process. In this paper, we argue that production scenarios demand high-precision, high-performance NL2SQL systems, rather than simply high-quality SQL generation, which is the focus of most current NL2SQL approaches. In such scenarios, the careful selection of a static set of exemplars-capturing the intricacies of the query log, target database, SQL constructs, and execution latencies-plays a more crucial role than exemplar selection based solely on similarity. The key challenge, however, lies in identifying a representative set of exemplars for a given production setting. To this end, we propose a prompt optimization framework that not only addresses the high-precision requirement but also optimizes the performance of the generated SQL through multi-objective optimization. Preliminary empirical analysis demonstrates the effectiveness of the proposed framework.

cs.CL↗

arXiv2025

Orchestrating Agents and Data for Enterprise: A Blueprint Architecture for Compound AI

Large language models (LLMs) have gained significant interest in industry due to their impressive capabilities across a wide range of tasks. However, the widespread adoption of LLMs presents several challenges, such as integration into existing applications and infrastructure, utilization of company proprietary data, models, and APIs, and meeting cost, quality, responsiveness, and other requirements. To address these challenges, there is a notable shift from monolithic models to compound AI systems, with the premise of more powerful, versatile, and reliable applications. However, progress thus far has been piecemeal, with proposals for agentic workflows, programming models, and extended LLM capabilities, without a clear vision of an overall architecture. In this paper, we propose a 'blueprint architecture' for compound AI systems for orchestrating agents and data for enterprise applications. In our proposed architecture the key orchestration concept is 'streams' to coordinate the flow of data and instructions among agents. Existing proprietary models and APIs in the enterprise are mapped to 'agents', defined in an 'agent registry' that serves agent metadata and learned representations for search and planning. Agents can utilize proprietary data through a 'data registry' that similarly registers enterprise data of various modalities. Tying it all together, data and task 'planners' break down, map, and optimize tasks and queries for given quality of service (QoS) requirements such as cost, accuracy, and latency. We illustrate an implementation of the architecture for a use-case in the HR domain and discuss opportunities and challenges for 'agentic AI' in the enterprise.

cs.AI↗

arXiv2025

MageSQL: Enhancing In-context Learning for Text-to-SQL Applications with Large Language Models

The text-to-SQL problem aims to translate natural language questions into SQL statements to ease the interaction between database systems and end users. Recently, Large Language Models (LLMs) have exhibited impressive capabilities in a variety of tasks, including text-to-SQL. While prior works have explored various strategies for prompting LLMs to generate SQL statements, they still fall short of fully harnessing the power of LLM due to the lack of (1) high-quality contextual information when constructing the prompts and (2) robust feedback mechanisms to correct translation errors. To address these challenges, we propose MageSQL, a text-to-SQL approach based on in-context learning over LLMs. MageSQL explores a suite of techniques that leverage the syntax and semantics of SQL queries to identify relevant few-shot demonstrations as context for prompting LLMs. In particular, we introduce a graph-based demonstration selection method -- the first of its kind in the text-to-SQL problem -- that leverages graph contrastive learning adapted with SQL-specific data augmentation strategies. Furthermore, an error correction module is proposed to detect and fix potential inaccuracies in the generated SQL query. We conduct comprehensive evaluations on several benchmarking datasets. The results show that our proposed methods outperform state-of-the-art methods by an obvious margin.

cs.DB↗

arXiv2025

Towards Operationalizing Heterogeneous Data Discovery

Querying and exploring massive collections of data sources, such as data lakes, has been an essential research topic in the database community. Although many efforts have been paid in the field of data discovery and data integration in data lakes, they mainly focused on the scenario where the data lake consists of structured tables. However, real-world enterprise data lakes are always more complicated, where there might be silos of multi-modal data sources with structured, semi-structured and unstructured data. In this paper, we envision an end-to-end system with declarative interface for querying and analyzing the multi-modal data lakes. First of all, we come up with a set of multi-modal operators, which is a unified interface that extends the relational operations with AI-composed ones to express analytical workloads over data sources in various modalities. In addition, we formally define the essential steps in the system, such as data discovery, query planning, query processing and results aggregation. On the basis of it, we then pinpoint the research challenges and discuss potential opportunities in realizing and optimizing them with advanced techniques brought by Large Language Models. Finally, we demonstrate our preliminary attempts to address this problem and suggest the future plan for this research topic.

cs.DB↗

arXiv2024

A Blueprint Architecture of Compound AI Systems for Enterprise

Large Language Models (LLMs) have showcased remarkable capabilities surpassing conventional NLP challenges, creating opportunities for use in production use cases. Towards this goal, there is a notable shift to building compound AI systems, wherein LLMs are integrated into an expansive software infrastructure with many components like models, retrievers, databases and tools. In this paper, we introduce a blueprint architecture for compound AI systems to operate in enterprise settings cost-effectively and feasibly. Our proposed architecture aims for seamless integration with existing compute and data infrastructure, with ``stream'' serving as the key orchestration concept to coordinate data and instructions among agents and other components. Task and data planners, respectively, break down, map, and optimize tasks and data to available agents and data sources defined in respective registries, given production constraints such as accuracy and latency.

cs.DB↗

arXiv2024

CMDBench: A Benchmark for Coarse-to-fine Multimodal Data Discovery in Compound AI Systems

Compound AI systems (CASs) that employ LLMs as agents to accomplish knowledge-intensive tasks via interactions with tools and data retrievers have garnered significant interest within database and AI communities. While these systems have the potential to supplement typical analysis workflows of data analysts in enterprise data platforms, unfortunately, CASs are subject to the same data discovery challenges that analysts have encountered over the years -- silos of multimodal data sources, created across teams and departments within an organization, make it difficult to identify appropriate data sources for accomplishing the task at hand. Existing data discovery benchmarks do not model such multimodality and multiplicity of data sources. Moreover, benchmarks of CASs prioritize only evaluating end-to-end task performance. To catalyze research on evaluating the data discovery performance of multimodal data retrievers in CASs within a real-world setting, we propose CMDBench, a benchmark modeling the complexity of enterprise data platforms. We adapt existing datasets and benchmarks in open-domain -- from question answering and complex reasoning tasks to natural language querying over structured data -- to evaluate coarse- and fine-grained data discovery and task execution performance. Our experiments reveal the impact of data retriever design on downstream task performance -- a 46% drop in task accuracy on average -- across various modalities, data sources, and task difficulty. The results indicate the need to develop optimization strategies to identify appropriate LLM agents and retrievers for efficient execution of CASs over enterprise data.

cs.DB↗

arXiv2024

Reasoning Capacity in Multi-Agent Systems: Limitations, Challenges and Human-Centered Solutions

Remarkable performance of large language models (LLMs) in a variety of tasks brings forth many opportunities as well as challenges of utilizing them in production settings. Towards practical adoption of LLMs, multi-agent systems hold great promise to augment, integrate, and orchestrate LLMs in the larger context of enterprise platforms that use existing proprietary data and models to tackle complex real-world tasks. Despite the tremendous success of these systems, current approaches rely on narrow, single-focus objectives for optimization and evaluation, often overlooking potential constraints in real-world scenarios, including restricted budgets, resources and time. Furthermore, interpreting, analyzing, and debugging these systems requires different components to be evaluated in relation to one another. This demand is currently not feasible with existing methodologies. In this postion paper, we introduce the concept of reasoning capacity as a unifying criterion to enable integration of constraints during optimization and establish connections among different components within the system, which also enable a more holistic and comprehensive approach to evaluation. We present a formal definition of reasoning capacity and illustrate its utility in identifying limitations within each component of the system. We then argue how these limitations can be addressed with a self-reflective process wherein human-feedback is used to alleviate shortcomings in reasoning and enhance overall consistency of the system.

cs.CL↗

arXiv2023

Towards Multifaceted Human-Centered AI

Human-centered AI workflows involve stakeholders with multiple roles interacting with each other and automated agents to accomplish diverse tasks. In this paper, we call for a holistic view when designing support mechanisms, such as interaction paradigms, interfaces, and systems, for these multifaceted workflows.

cs.DB↗

arXiv2023

MEGAnno: Exploratory Labeling for NLP in Computational Notebooks

We present MEGAnno, a novel exploratory annotation framework designed for NLP researchers and practitioners. Unlike existing labeling tools that focus on data labeling only, our framework aims to support a broader, iterative ML workflow including data exploration and model development. With MEGAnno's API, users can programmatically explore the data through sophisticated search and automated suggestion functions and incrementally update task schema as their project evolve. Combined with our widget, the users can interactively sort, filter, and assign labels to multiple items simultaneously in the same notebook where the rest of the NLP project resides. We demonstrate MEGAnno's flexible, exploratory, efficient, and seamless labeling experience through a sentiment analysis use case.

cs.HC↗

arXiv2022

Machop: an End-to-End Generalized Entity Matching Framework

Real-world applications frequently seek to solve a general form of the Entity Matching (EM) problem to find associated entities. Such scenarios include matching jobs to candidates in job targeting, matching students with courses in online education, matching products with user reviews on e-commercial websites, and beyond. These tasks impose new requirements such as matching data entries with diverse formats or having a flexible and semantics-rich matching definition, which are beyond the current EM task formulation or approaches. In this paper, we introduce the problem of Generalized Entity Matching (GEM) that satisfies these practical requirements and presents an end-to-end pipeline Machop as the solution. Machop allows end-users to define new matching tasks from scratch and apply them to new domains in a step-by-step manner. Machop casts the GEM problem as sequence pair classification so as to utilize the language understanding capability of Transformers-based language models (LMs) such as BERT. Moreover, it features a novel external knowledge injection approach with structure-aware pooling methods that allow domain experts to guide the LM to focus on the key matching information thus further contributing to the overall performance. Our experiments and case studies on real-world datasets from a popular recruiting platform show a significant 17.1% gain in F1 score against state-of-the-art methods along with meaningful matching results that are human-understandable.

cs.DB↗

arXiv2020

IBM Functional Genomics Platform, A Cloud-Based Platform for Studying Microbial Life at Scale

The rapid growth in biological sequence data is revolutionizing our understanding of genotypic diversity and challenging conventional approaches to informatics. With the increasing availability of genomic data, traditional bioinformatic tools require substantial computational time and the creation of ever-larger indices each time a researcher seeks to gain insight from the data. To address these challenges, we pre-computed important relationships between biological entities spanning the Central Dogma of Molecular Biology and captured this information in a relational database. The database can be queried across hundreds of millions of entities and returns results in a fraction of the time required by traditional methods. In this paper, we describe \textit{IBM Functional Genomics Platform} (formerly known as OMXWare), a comprehensive database relating genotype to phenotype for bacterial life. Continually updated, IBM Functional Genomics Platform today contains data derived from 200,000 curated, self-consistently assembled genomes. The database stores functional data for over 68 million genes, 52 million proteins, and 239 million domains with associated biological activity annotations from Gene Ontology, KEGG, MetaCyc, and Reactome. IBM Functional Genomics Platform maps all of the many-to-many connections between each biological entity including the originating genome, gene, protein, and protein domain. Various microbial studies, from infectious disease to environmental health, can benefit from the rich data and connections. We describe the data selection, the pipeline to create and update the IBM Functional Genomics Platform, and the developer tools (Python SDK and REST APIs) which allow researchers to efficiently study microbial life at scale.

q-bio.QM↗

arXiv2019

HEIDL: Learning Linguistic Expressions with Deep Learning and Human-in-the-Loop

While the role of humans is increasingly recognized in machine learning community, representation of and interaction with models in current human-in-the-loop machine learning (HITL-ML) approaches are too low-level and far-removed from human's conceptual models. We demonstrate HEIDL, a prototype HITL-ML system that exposes the machine-learned model through high-level, explainable linguistic expressions formed of predicates representing semantic structure of text. In HEIDL, human's role is elevated from simply evaluating model predictions to interpreting and even updating the model logic directly by enabling interaction with rule predicates themselves. Raising the currency of interaction to such semantic levels calls for new interaction paradigms between humans and machines that result in improved productivity for text analytics model development process. Moreover, by involving humans in the process, the human-machine co-created models generalize better to unseen data as domain experts are able to instill their expertise by extrapolating from what has been learned by automated algorithms from few labelled data.

cs.CL↗