# ProfiliTable: Profiling-Driven Tabular Data Processing via Agentic Workflows

Source: [ProfiliTable: Profiling-Driven Tabular Data Processing via Agentic Workflows](<https://www.sota2.com/research/paper/6a0405e4dbc836b87d827948>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-06-06T05:00:11.965Z

Authors: Wei Liu, Yang Gu, Xi Yan, Zihan Nan, Beicheng Xu, Keyao Ding, Bin Cui, Wentao Zhang

Published: 2026-05-12T16:42:38.000Z

## Abstract

Table processing-including cleaning, transformation, augmentation, and matching-is a foundational yet error-prone stage in real-world data pipelines. While recent LLM-based approaches show promise for automating such tasks, they often struggle in practice due to ambiguous instructions, complex task structures, and the lack of structured feedback, resulting in syntactically correct but semantically flawed code. To address these challenges, we propose ProfiliTable, an autonomous multi-agent framework centered on dynamic profiling, which constructs and iteratively refines a unified execution context through interactive exploration, knowledge-augmented synthesis, and feedback-driven refinement. ProfiliTable integrates (i) a Profiler that performs ReAct-style data exploration to build semantic understanding, (ii) a Generator that retrieves curated operators to synthesize task-aware code, and (iii) an Evaluator-Summarizer loop that injects execution scores and diagnostic insights to enable closed-loop refinement. Extensive experiments on a diverse benchmark covering 18 tabular task types demonstrate that ProfiliTable consistently outperforms strong baselines, particularly in complex multi-step scenarios. These results highlight the critical role of dynamic profiling in reliably translating ambiguous user intents into robust and governance-compliant table transformations.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Tabular Data Processing on ProfiliTable single-step 1.0 (test)](<https://www.sota2.com/research/sota/tabular-data-processing-on-profilitable-single-step-1-0-test.md>): Tabular Data Processing; ProfiliTable single-step 1.0 (test); ATS: 89.66.

- [Multi-step Tabular Data Processing on Multi-step tabular data processing tasks](<https://www.sota2.com/research/sota/multi-step-tabular-data-processing-on-multi-step-tabular-data-processing-tasks.md>): Multi-step tabular data processing; Multi-step tabular data processing tasks; ATS: 82.49.

- [Tabular Data Processing on ProfiliTable multi-step 1.0 (test)](<https://www.sota2.com/research/sota/tabular-data-processing-on-profilitable-multi-step-1-0-test.md>): Tabular Data Processing; ProfiliTable multi-step 1.0 (test); ATS: not recorded.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2605.12376>)

[PDF](<https://arxiv.org/pdf/2605.12376.pdf>)