TADA-Agent, whose atoms run inside generated Python programs and internally handle inputs beyond a reliable context window, delivers comparable row-level semantic quality, has higher complete-artifact preservation estimates, and uses over an order of magnitude fewer semantic-model requests under the evaluated native execution paths.
Abstract
Much of the information needed for data analysis is buried in text columns: an analyst may infer customer frustration from complaint text and use it to explain resolution time. We call workloads in which processing text columns is central to subsequent data analysis TADA (\emph{Text Analysis in Data Analytics}). In an agentic setting, the user's query dynamically specifies this processing, and answering it interleaves LLM-based semantic steps with exact SQL or Python operations. This mixed execution raises two design questions: which work should be neural and which symbolic, and which semantic outputs later steps can reuse. We address them for agent-planned TADA workflows with two complementary, query-driven semantic atoms. Each atom takes a sequence of text items and a natural-language query specifying the semantic task: \textbf{Tagging} returns one string per input item, while \textbf{Categorization} returns $M$ category objects over $N$ input items. Tagging results are materialized as a row-aligned column and Categorization results as a category table; SQL or Python then performs exact computation over this exposed state. We realize this interface in TADA-Agent, whose atoms run inside generated Python programs and internally handle inputs beyond a reliable context window. We evaluate TADA-Agent on TABench, a benchmark of 40 complete analysis requests over spreadsheet tables spanning workflow composition, input--output structure, and literature-grounded analytical scenarios. Against a semantic-operator baseline and relative to a held-out TADA reference run, TADA-Agent delivers comparable row-level semantic quality, has higher complete-artifact preservation estimates, and uses over an order of magnitude fewer semantic-model requests under the evaluated native execution paths.
LLM-based data systems are moving beyond text-to-SQL toward semantic query processing, where natural language requests are executed through operators that combine relational processing with LLM-driven inference. A central operator in this setting is SemanticRank, or semantic top-k: given a user intent and a set of rela...
E. Lenzi, D. Martinenghi, Paolo Papotti et al.· Proceedings of the 35th ACM...· 0 citations
Text-to-SQL translates natural language questions into SQL queries, enabling database access without writing SQL. Fine-tuning open-weight large language models (LLMs) is cost-effective, but existing methods treat SQL as ordinary text and optimize token-level likelihood without explicitly modeling its syntactic, semanti...
Non-technical stakeholders frequently cannot write the SQL needed to extract insights from operational databases. We built and evaluated a Text-to-SQL agent that closes this gap end to end: a six-node LangGraph StateGraph checks question relevance, fetches the live schema, generates PostgreSQL, validates it with a dry...
It is shown that for database queries, data model concepts pass to LLMs more effectively through representations whose vocabulary terms carry declared, machine-readable semantics (controlled semantics).
QRAKEN is a training-free, ontology-agnostic neurosymbolic pipeline grounding generation in empirical graph evidence rather than schema expectations, supporting the value of empirical patterns beyond schema exposure.
Remo Grillo, L. Klic, Giovanni Colavizza· 0 citations
Text-to-SQL data synthesis must expand semantic coverage without losing the relational structure of observed queries. Existing SQL offers evidence of plausible join and nesting patterns, but reusing queries alone limits the range of training examples; unconstrained generation, in contrast, risks implausible structures...
Hao-Yu Zhang, Ying-Qi Zou, Xiang-Yu Wang et al.· Information· 0 citations