Toward Reliable Scientific Visualization Pipeline Construction with Structure-Aware Retrieval-Augmented LLMs

• URL: http://arxiv.org/abs/2603.16057v1
• Date: Tue, 17 Mar 2026 01:52:11 GMT
• Title: Toward Reliable Scientific Visualization Pipeline Construction with Structure-Aware Retrieval-Augmented LLMs
• Abstract summary: We propose a structure-aware retrieval-augmented generation workflow that provides pipeline-aligned vtk.js code examples as contextual guidance.<n>We show that structured, domain-specific context substantially improves pipeline executability and reduces correction cost.
• Score: 8.621769369142395
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Scientific visualization pipelines encode domain-specific procedural knowledge with strict execution dependencies, making their construction sensitive to missing stages, incorrect operator usage, or improper ordering. Thus, generating executable scientific visualization pipelines from natural-language descriptions remains challenging for large language models, particularly in web-based environments where visualization authoring relies on explicit code-level pipeline assembly. In this work, we investigate the reliability of LLM-based scientific visualization pipeline generation, focusing on vtk.js as a representative web-based visualization library. We propose a structure-aware retrieval-augmented generation workflow that provides pipeline-aligned vtk.js code examples as contextual guidance, supporting correct module selection, parameter configuration, and execution order. We evaluate the proposed workflow across multiple multi-stage scientific visualization tasks and LLMs, measuring reliability in terms of pipeline executability and human correction effort. To this end, we introduce correction cost as metric for the amount of manual intervention required to obtain a valid pipeline. Our results show that structured, domain-specific context substantially improves pipeline executability and reduces correction cost. We additionally provide an interactive analysis interface to support human-in-the-loop inspection and systematic evaluation of generated visualization pipelines.

Related papers

• Evaluating Modern RAG: Textual, Multimodal, Dense, and Late Interaction Pipelines [1.4180331276028662]
  Retrieval-augmented generation (RAG) systems have traditionally relied on text-based pipelines that extract and retrieve information from documents.<n>Recent advances in multimodal pipelines, powered by vision-language models (VLMs), improve retrieval quality by jointly encoding visual and textual signals, but at increased computational and memory cost.<n>We evaluate contemporary textual and multimodal pipelines, including dense and late-interaction architectures, analyze their trade-offs, and provide actionable guidance for balancing retrieval performance with system efficiency.
  arXiv  Detail & Related papers  (2026-08-24T12:25:52Z)
• RepoReasoner: Evaluating Repository-Level Code Reasoning Ability of Long-Context Language Models [54.53236295237077]
  We introduce RepoReasoner, a benchmark for evaluating repository-level code reasoning.<n> Output Prediction measures fine-grained, stateful execution reasoning across files.<n>Call Chain Prediction evaluates high-level architectural dependency understanding under noisy context.
  arXiv  Detail & Related papers  (2026-07-28T17:12:41Z)
• SemPiper: Interactive Code Synthesis for Semantic Operators in Machine Learning Pipelines [7.868559688632956]
  We demonstrate SemPipes, a programming model that extends machine learning pipelines with semantic data operators.<n>For the semantic operators, SemPipes synthesizes specialized implementations at pipeline training time.<n>We show how semantic operators enable controllable, optimizable, and practical integration of LLMs into ML pipeline development.
  arXiv  Detail & Related papers  (2026-06-12T11:40:09Z)
• PARM: Pipeline-Adapted Reward Model [60.769414637325326]
  Reward models (RMs) are central to aligning large language models (LLMs) with human preferences, powering advanced decoding strategies.<n>While most prior work focuses on single-step generation, real-world applications increasingly adopt multi-stage pipelines.<n>We investigate this through code generation for optimization, constructing a pipeline that integrates reward models into both formulation and solution stages.
  arXiv  Detail & Related papers  (2026-04-20T14:29:08Z)
• kRAIG: A Natural Language-Driven Agent for Automated DataOps Pipeline Generation [0.5833117322405447]
  We introduce kRAIG, an AI agent that translates natural language specifications into production-ready KubeReason Pipelines (KFP)<n>To resolve ambiguity in user intent, we propose ReQuesAct, an interaction framework that explicitly clarifies intent prior to pipeline synthesis.<n>Our framework achieves a 3x improvement in extraction and loading success and a 25 percent increase in transformation accuracy compared to state-of-the-art agentic baselines.
  arXiv  Detail & Related papers  (2026-03-19T17:53:00Z)
• Autonomous Data Processing using Meta-Agents [2.3732259124656907]
  We present textbfAutonomous Data Processing using Meta-agents (ADP-MA), a framework that dynamically constructs, executes, and iteratively refines data processing pipelines.<n> ADP-MA emphasizes context-aware optimization, adaptive workload partitioning, and progressive sampling for scalability.<n>We demonstrate ADP-MA through an interactive demo that showcases pipeline construction, execution monitoring, and adaptive refinement across representative data processing tasks.
  arXiv  Detail & Related papers  (2026-01-30T20:58:17Z)
• A Dialectic Pipeline for Improving LLM Robustness [0.0]
  Methods such as fine-tuning on domain-specific data or the training of a separate textitad hoc verifier require demanding computational resources.<n>We propose a dialectic pipeline that preserves LLMs' generalization abilities while improving the quality of its answer via self-dialogue.<n>We find that our proposed dialectic pipeline is able to outperform by significative margins the standard model answers.
  arXiv  Detail & Related papers  (2026-01-28T14:42:49Z)
• AI Agent for Reverse-Engineering Legacy Finite-Difference Code and Translating to Devito [0.0]
  This study develops an integrated AI framework to facilitate the transformation of legacy finite difference implementations into the Devito environment.<n>Retrieval-Augmented Generation (RAG) and open-source Large Language Models are combined through multi-stage iterative in the system's hybrid LangGraph architecture.
  arXiv  Detail & Related papers  (2026-01-26T11:31:00Z)
• Operon: Incremental Construction of Ragged Data via Named Dimensions [1.6212518002538465]
  Existing workflow engines lack native support for tracking the shapes and dependencies inherent to ragged data.<n>We present Operon, a Rust-based workflow engine that addresses these challenges through a novel formalism of named dimensions with explicit dependency relations.
  arXiv  Detail & Related papers  (2025-11-20T06:16:31Z)
• ContextNav: Towards Agentic Multimodal In-Context Learning [85.05420047017513]
  ContextNav is an agentic framework that integrates the scalability of automated retrieval with the quality and adaptiveness of human-like curation.<n>It builds a resource-aware multimodal embedding pipeline, maintains a retrievable vector database, and applies agentic retrieval and structural alignment to construct noise-resilient contexts.<n> Experimental results demonstrate that ContextNav achieves state-of-the-art performance across various datasets.
  arXiv  Detail & Related papers  (2025-10-06T07:49:52Z)
• Text-to-Pipeline: Bridging Natural Language and Data Preparation Pipelines [18.75611679837171]
  We introduce Text-to-Pipeline, a new task that translates NL data preparation instructions into DP pipelines.<n>Parrot is a large-scale benchmark to support systematic evaluation.<n>ParROT is built by mining transformation patterns from production pipelines and instantiating them on 23,009 real-world tables.
  arXiv  Detail & Related papers  (2025-05-21T15:40:53Z)
• Benchmarking Agentic Workflow Generation [80.74757493266057]
  We introduce WorfBench, a unified workflow generation benchmark with multi-faceted scenarios and intricate graph workflow structures.<n>We also present WorfEval, a systemic evaluation protocol utilizing subsequence and subgraph matching algorithms.<n>We observe that the generated can enhance downstream tasks, enabling them to achieve superior performance with less time during inference.
  arXiv  Detail & Related papers  (2024-10-10T12:41:19Z)
• In-context Demonstration Matters: On Prompt Optimization for Pseudo-Supervision Refinement [71.60563181678323]
  Large language models (LLMs) have achieved great success across diverse tasks, and fine-tuning is sometimes needed to further enhance generation quality.<n>To handle these challenges, a direct solution is to generate high-confidence'' data from unsupervised downstream tasks.<n>We propose a novel approach, pseudo-supervised demonstrations aligned prompt optimization (PAPO) algorithm, which jointly refines both the prompt and the overall pseudo-supervision.
  arXiv  Detail & Related papers  (2024-10-04T03:39:28Z)
• Instruction Tuning for Large Language Models: A Survey [52.86322823501338]
  We make a systematic review of the literature, including the general methodology of supervised fine-tuning (SFT)<n>We also review the potential pitfalls of SFT along with criticism against it, along with efforts pointing out current deficiencies of existing strategies.
  arXiv  Detail & Related papers  (2023-08-21T15:35:16Z)
• Demonstrate-Search-Predict: Composing retrieval and language models for knowledge-intensive NLP [77.817293104436]
  We propose a framework that relies on passing natural language texts in sophisticated pipelines between an LM and an RM. We have written novel DSP programs for answering questions in open-domain, multi-hop, and conversational settings.
  arXiv  Detail & Related papers  (2022-12-28T18:52:44Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.