mlsanityData to 7 Oct 2026

Agentic Insight Generation in VSM Simulations

arXiv 2604.12421 ↗First posted 14 Apr 2026cs.CLcited by 0

On the map: LLM agents and tool use → General LLM agent frameworks and benchmarks

Abstract (arXiv)

Extracting actionable insights from complex value stream map simulations can be challenging, time-consuming, and error-prone. Recent advances in large language models offer new avenues to support users with this task. While existing approaches excel at processing raw data to gain information, they are structurally unfit to pick up on subtle situational differences needed to distinguish similar data sources in this domain. To address this issue, we propose a decoupled, two-step agentic architecture. By separating orchestration from data analysis, the system leverages progressive data discovery infused with domain expert knowledge. This architecture allows the orchestration to intelligently select data sources and perform multi-hop reasoning across data structures while maintaining a slim internal context. Results from multiple state-of-the-art large language models demonstrate the framework's viability: with top-tier models achieving accuracies of up to 86% and demonstrating high robustness across evaluation runs.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use. Builds on 18 of its 31 references that are in the map. First posted on arXiv 14 Apr 2026.

Builds on

18 of 31 references.

Closest ancestors · 1

Same direction, newest first

  1. 2024Personal LLM Agents: Insights and Survey about the Capability, Efficiency and Security10 Jan

Other references · 17

  1. 2024The Llama 3 Herd of Modelscited by 14,192
  2. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  3. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  4. 2025Qwen3 Technical Reportcited by 8,195
  5. 2023Efficient Memory Management for Large Language Model Serving with PagedAttentioncited by 5,767
  6. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,800
  7. 2023Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generationcited by 795
  8. 2021Retrieval Augmentation Reduces Hallucination in Conversationcited by 691
  9. 2019Quantifying the Carbon Emissions of Machine Learningcited by 516
  10. 2026GLM-5: from Vibe Coding to Agentic Engineeringcited by 502
  11. 2025The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Searchcited by 375
  12. 2022Demonstrate-Search-Predict: Composing retrieval and language models for knowledge-intensive NLPcited by 316
5 more
  1. 2024ProSA: Assessing and Understanding the Prompt Sensitivity of LLMscited by 145
  2. 2025A Survey on Code Generation with LLM-based Agentscited by 104
  3. 2023TaskWeaver: A Code-First Agent Frameworkcited by 85
  4. 2023Large Language Models for Supply Chain Optimizationcited by 61
  5. 2024The Open Source Advantage in Large Language Models (LLMs)cited by 18

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025InsightEval: An Expert-Curated Benchmark for Assessing Insight Discovery in LLM-Driven Data Agents
  2. 2025Agentic Reasoning: A Streamlined Framework for Enhancing LLM Reasoning with Agentic Tools
  3. 2026Exploring Autonomous Agentic Data Engineering for Model Specialization
  4. 2026What Makes Good Agentic Data? An ACE Lens on Data Generation for LLM Agents
  5. 2026Environment Maps: Structured Environmental Representations for Long-Horizon Agents
  6. 2025Simulation Agent: A Framework for Integrating Simulation and Large Language Models for Enhanced Decision-Making
  7. 2025FABRIC: Framework for Agent-Based Realistic Intelligence Creation
  8. 2026FROAV: A Framework for RAG Observation and Agent Verification -- Lowering the Barrier to LLM Agent Research