# TopoPilot: Reliable Conversational Workflow Automation for Topological Data Analysis and Visualization arXiv: https://arxiv.org/abs/2603.25063 ยท HTML: https://mlsanity.com/paper/2603.25063/ ## Key facts - Cited by 3 papers in the map (data through 14 Oct 2026). - Placed in Multimodal and embodied agents, one of 16 directions in LLM agents and tool use. - Builds on 35 of its 74 references that are in the map. - First posted on arXiv 26 Mar 2026. ## Placed in - LLM agents and tool use / [Multimodal and embodied agents](https://mlsanity.com/agents/multimodal-and-embodied-agents/) ## Builds on (most cited first, 30 of 35) - [Language Agent Tree Search Unifies Reasoning Acting and Planning in Language Models](https://mlsanity.com/paper/2310.04406/) (2023) - [ToolChain*: Efficient Action Space Navigation in Large Language Models with A* Search](https://mlsanity.com/paper/2310.13227/) (2023) - [MatPlotAgent: Method and Evaluation for LLM-Based Agentic Scientific Data Visualization](https://mlsanity.com/paper/2402.11453/) (2024) - [ChartGPT: Leveraging LLMs to Generate Charts from Abstract Natural Language](https://mlsanity.com/paper/2311.01920/) (2023) - [TrustAgent: Towards Safe and Trustworthy LLM-based Agents](https://mlsanity.com/paper/2402.01586/) (2024) - [Chat2VIS: Generating Data Visualisations via Natural Language using ChatGPT, Codex and GPT-3 Large Language Models](https://mlsanity.com/paper/2302.02094/) (2023) - [Current state of LLM Risks and AI Guardrails](https://mlsanity.com/paper/2406.12934/) (2024) - [The Topology ToolKit](https://mlsanity.com/paper/1805.09110/) (2018) - [Tool-Planner: Task Planning with Clusters across Multiple Tools](https://mlsanity.com/paper/2406.03807/) (2024) - [AI4VIS: Survey on Artificial Intelligence Approaches for Data Visualization](https://mlsanity.com/paper/2102.01330/) (2021) - [Measuring and Reducing LLM Hallucination without Gold-Standard Answers](https://mlsanity.com/paper/2402.10412/) (2024) - [DataNarrative: Automated Data-Driven Storytelling with Visualizations and Texts](https://mlsanity.com/paper/2408.05346/) (2024) - [Advancing Agentic Systems: Dynamic Task Decomposition, Tool Integration and Evaluation using Novel Metrics and Dataset](https://mlsanity.com/paper/2410.22457/) (2024) - [AVA: Towards Autonomous Visualization Agents through Visual Perception-Driven Decision-Making](https://mlsanity.com/paper/2312.04494/) (2023) - [LightVA: Lightweight Visual Analytics with LLM Agent-Based Task Planning and Execution](https://mlsanity.com/paper/2411.05651/) (2024) - [NLI4VolVis: Natural Language Interaction for Volume Visualization via LLM Multi-Agents and Editable 3D Gaussian Splatting](https://mlsanity.com/paper/2507.12621/) (2025) - [CoDA: Agentic Systems for Collaborative Data Visualization](https://mlsanity.com/paper/2510.03194/) (2025) - [ToolGate: Contract-Grounded and Verified Tool Execution for LLMs](https://mlsanity.com/paper/2601.04688/) (2026) - [Scalar Field Comparison with Topological Descriptors: Properties and Applications for Scientific Visualization](https://mlsanity.com/paper/2106.00157/) (2021) - [ProactiveVA: Proactive Visual Analytics with LLM-Based UI Agent](https://mlsanity.com/paper/2507.18165/) (2025) - [ChatVis: Automating Scientific Visualization with a Large Language Model](https://mlsanity.com/paper/2410.11863/) (2024) - [ParaView-MCP: An Autonomous Visualization Agent with Direct Tool Use](https://mlsanity.com/paper/2505.07064/) (2025) - [VizGenie: Toward Self-Refining, Domain-Aware Workflows for Next-Generation Scientific Visualization](https://mlsanity.com/paper/2507.21124/) (2025) - [Automated Visualization Code Synthesis via Multi-Path Reasoning and Feedback-Driven Optimization](https://mlsanity.com/paper/2502.11140/) (2025) - [ChatVis: Large Language Model Agent for Generating Scientific Visualizations](https://mlsanity.com/paper/2507.23096/) (2025) - [Text-based Transfer Function Design for Semantic Volume Rendering](https://mlsanity.com/paper/2406.15634/) (2024) - [Using Contour Trees in the Analysis and Visualization of Radio Astronomy Data Cubes](https://mlsanity.com/paper/1704.04561/) (2017) - [The Six Sigma Agent: Achieving Enterprise-Grade Reliability in LLM Systems Through Consensus-Driven Decomposed Execution](https://mlsanity.com/paper/2601.22290/) (2026) - [Parallel Computation of Piecewise Linear Morse-Smale Segmentations](https://mlsanity.com/paper/2303.15491/) (2023) - [TROPHY: A Topologically Robust Physics-Informed Tracking Framework for Tropical Cyclones](https://mlsanity.com/paper/2307.15243/) (2023) ## Built on by (most cited first, 3 of 3) - [SciVisAgentBench: A Benchmark for Evaluating Scientific Data Analysis and Visualization Agents](https://mlsanity.com/paper/2603.29139/) (2026) - [HiLSVA: Design and Evaluation of a Human-in-the-Loop Agentic System for Scientific Visualization](https://mlsanity.com/paper/2606.26614/) (2026) - [SciVisAgentSkills: Design and Evaluation of Agent Skills for Scientific Data Analysis and Visualization](https://mlsanity.com/paper/2606.05525/) (2026) ## Abstract (arXiv) Recent agentic systems demonstrate that large language models can generate complex codebases from natural language prompts. Despite this progress, they present reliability concerns for scientific visualization due to invalid operations, subtle errors, and failure to resolve underspecified inputs. These challenges are compounded in real-world workflows that exceed the complexity of standard benchmarks. In this work, we introduce TopoPilot, a reliable and extensible agentic framework for automating complex scientific visualization workflows. We focus on topological data analysis and visualization as a primary use case, while designing the framework to generalize to broader visualization domains. TopoPilot employs a two-agent architecture: an orchestrator translates user prompts into workflows composed of atomic backend actions, while a verifier evaluates workflows prior to execution. Its modular design isolates components and supports new topological descriptors and domain-specific workflows without modifying the core system. It also employs numerous deterministic guardrails to ensure semantic consistency and accurate execution. To systematically improve reliability, we develop a taxonomy of failure modes and employ targeted safeguards for each class of error. Across 1,000 simulated multi-turn conversations spanning 100 prompts, including adversarial and infeasible requests, TopoPilot achieves a success rate exceeding 95%, compared with under 50% for a baseline without comprehensive guardrails and verification. We also show that TopoPilot outperforms Claude Code and Codex on similar prompts in terms of accuracy, completion time, and token usage.