# LLM Agents for Interactive Workflow Provenance: Reference Architecture and Evaluation Methodology

arXiv: https://arxiv.org/abs/2509.13978 · HTML: https://mlsanity.com/paper/2509.13978/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Placed in Web, search, and research agents, one of 16 directions in LLM agents and tool use.
- Builds on 12 of its 26 references that are in the map.
- First posted on arXiv 17 Sep 2025.

## Placed in

- LLM agents and tool use / [Web, search, and research agents](https://mlsanity.com/agents/web-search-and-research-agents/)

## Builds on (most cited first, 12 of 12)

- [A Survey on LLM-as-a-Judge](https://mlsanity.com/paper/2411.15594/) (2024)
- [Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLs](https://mlsanity.com/paper/2305.03111/) (2023)
- [PROV-AGENT: Unified Provenance for Tracking AI Agent Interactions in Agentic Workflows](https://mlsanity.com/paper/2508.02866/) (2025)
- [The HaLLMark Effect: Supporting Provenance and Transparent Use of Large Language Models in Writing with Interactive Visualization](https://mlsanity.com/paper/2311.13057/) (2023)
- [Towards Scalable Dataframe Systems](https://mlsanity.com/paper/2001.00888/) (2020)
- [Empowering Scientific Workflows with Federated Agents](https://mlsanity.com/paper/2505.05428/) (2025)
- [Workflow Provenance in the Lifecycle of Scientific Machine Learning](https://mlsanity.com/paper/2010.00330/) (2020)
- [Towards Lightweight Data Integration using Multi-workflow Provenance and Data Observability](https://mlsanity.com/paper/2308.09004/) (2023)
- [A Terminology for Scientific Workflow Systems](https://mlsanity.com/paper/2506.07838/) (2025)
- [A Grassroots Network and Community Roadmap for Interconnected Autonomous Science Laboratories for Accelerated Discovery](https://mlsanity.com/paper/2506.17510/) (2025)
- [Knowledge Transfer from LLMs to Provenance Analysis: A Semantic-Augmented Method for APT Detection](https://mlsanity.com/paper/2503.18316/) (2025)
- [TableVault: Managing Dynamic Data Collections for LLM-Augmented Workflows](https://mlsanity.com/paper/2506.18257/) (2025)

## Built on by (most cited first, 10 of 10)

- [Autonomous Research Agents: A Survey of AI Scientists and the Verification Gap](https://mlsanity.com/paper/2608.05179/) (2026)
- [Fantastic Scientific Agents and How to Build Them: AgentBuild for Rietveld Refinement](https://mlsanity.com/paper/2606.12834/) (2026)
- [From Agent Loops to Deterministic Graphs: Execution Lineage for Reproducible AI-Native Work](https://mlsanity.com/paper/2605.06365/) (2026)
- [ADEMA: A Knowledge-State Orchestration Architecture for Long-Horizon Knowledge Synthesis with LLMAgents](https://mlsanity.com/paper/2604.25849/) (2026)
- [Automated Data Readiness for Scientific AI](https://mlsanity.com/paper/2607.02771/) (2026)
- [Intermediate Artifacts as First-Class Citizens: A Data Model for Durable Intermediate Artifacts in Agentic Systems](https://mlsanity.com/paper/2605.12087/) (2026)
- [Workflow as Knowledge: Semantic Persistence for LLM-Mediated Workflows](https://mlsanity.com/paper/2607.08740/) (2026)
- [Schema-Bound LLM Control of Scientific Instrumentation through Model Context Protocol Skills](https://mlsanity.com/paper/2607.17012/) (2026)
- [Workflow Cards: Structured Summaries of Workflow Executions Using Provenance Data](https://mlsanity.com/paper/2608.11022/) (2026)
- [ECAS: An Edge-Controlled Agentic System for Validation-Gated Scientific Application Execution](https://mlsanity.com/paper/2609.14211/) (2026)

## Abstract (arXiv)

Modern scientific discovery increasingly relies on workflows that process data across the Edge, Cloud, and High Performance Computing (HPC) continuum. Comprehensive and in-depth analyses of these data are critical for hypothesis validation, anomaly detection, reproducibility, and impactful findings. Although workflow provenance techniques support such analyses, at large scale, the provenance data become complex and difficult to analyze. Existing systems depend on custom scripts, structured queries, or static dashboards, limiting data interaction. In this work, we introduce an evaluation methodology, reference architecture, and open-source implementation that leverages interactive Large Language Model (LLM) agents for runtime data analysis. Our approach uses a lightweight, metadata-driven design that translates natural language into structured provenance queries. Evaluations across LLaMA, GPT, Gemini, and Claude, covering diverse query classes and a real-world chemistry workflow, show that modular design, prompt tuning, and Retrieval-Augmented Generation (RAG) enable accurate and insightful LLM agent responses beyond recorded provenance.