Agentic Data Cleaning Without a Clean Reference: An Experimental Study of Capabilities and Trade-offs

[2608.14765] Agentic Data Cleaning Without a Clean Reference: An Experimental Study of Capabilities and Trade-offs Skip to main content Search Submit Donate Log in Search arXiv Press Enter to search · Advanced search Computer Science > Artificial Intelligence arXiv:2608.14765 (cs) [Submitted on 14 Aug 2026] Title: Agentic Data Cleaning Without a Clean Reference: An Experimental Study of Capabilities and Trade-offs Authors: Hadi Fadlallah View a PDF of the paper titled Agentic Data Cleaning Without a Clean Reference: An Experimental Study of Capabilities and Trade-offs, by Hadi Fadlallah View PDF HTML (experimental) Abstract: Data cleaning without a trusted clean reference is challenging because unusual values may represent either genuine errors or valid observations. This paper studies how different agent capabilities affect reference-free data cleaning and proposes an evidence-grounded framework that combines structured context, profiling, LLM reasoning, executable checks, controlled evidence retrieval, source ranking, citation alignment, conservative repair, reversible scripts, and provenance logging. Seven configurations are evaluated across financial, clinical, and environmental-monitoring datasets using controlled synthetic corruption and original-data descriptive analysis, resulting in 126 completed runs. The evaluation includes two comparison baselines and a progressive LLM-based sequence that adds executable tools, evidence retrieval, evidence controls, and conservative repair. In the synthetic evaluation, the deterministic profiling baseline achieved the highest detection F1-score of 0.561. Among the LLM-based configurations, the full conservative configuration achieved the highest F1-score of 0.421, but no configuration performed best across all evaluation criteria. The source-ranked configurations achieved the lowest unsupported-rule rates, while decision-level citation alignment remained weak. The full conservative configuration produced no unsafe or unnecessary modifications, although these rates were already zero before the conservative policy was added, and it performed no direct repairs. Overall, the results show that additional capabilities introduce trade-offs among detection, repair, evidence grounding, conservative behaviour, reproducibility, and operational cost rather than producing consistent improvements. The study provides a structured framework and empirical methodology for evaluating these trade-offs in reference-free agentic data cleaning. Comments: 21 pages, 3 figures, Submitted to New Generation Computing Subjects: Artificial Intelligence (cs.AI) ; Databases (cs.DB) Cite as: arXiv:2608.14765 [cs.AI] (or arXiv:2608.14765v1 [cs.AI] for this version) https://doi.org/10.48550/arXiv.2608.14765 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Hadi Fadlallah [ view email ] [v1] Fri, 14 Aug 2026 11:55:53 UTC (180 KB) Full-text links: Access Paper: View a PDF of the paper titled Agentic Data Cleaning Without a Clean Reference: An Experimental Study of Capabilities and Trade-offs, by Hadi Fadlallah View PDF HTML (experimental) TeX Source view license Current browse context: cs.AI < prev | next > new | recent | 2026-08 Change to browse by: cs cs.DB References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Loading... BibTeX formatted citation × loading... Data provided by: Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) scite.ai Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) We gratefully acknowledge support from our major funders , member institutions , , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab) Major funding support from

Related documents

• Agentic Data Cleaning Without a Clean Reference: An Experimental Study of Capabilities and Trade-offs#459766
• Evaluating Agentic Code Repair Capabilities in Distributed Systems#609283
• Evaluating Agentic Code Repair Capabilities in Distributed Systems#459635
• Configuration Smells in AGENTS.md Files: Common Mistakes in Configuring Coding Agents#282881
• AgentModernize: Preserving Business Logic in Legacy Modernization with Multi-Agent LLMs and Behavioral Specification Graphs#200560