Research map / Large language models / Agents, code and math
Agentic AI for Digital Twin
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Presents an interactive agentic LLM demo that orchestrates digital-twin tools (anomaly detection, work-order generation, forecasting, edge deployment) for shipping operations.
Problem
Digital twins for the shipping industry are hard to scale because of complex operations, dynamic drivers, and heterogeneous data sources, and they are difficult for diverse stakeholders to access.
Approach
An LLM planning and reflection agent (built with LangGraph) selects among digital-twin tools and data streams from natural-language queries, using a knowledge graph and edge orchestration so that language serves as a universal interface to the digital twin.
Key results
- No quantitative results are reported; the paper demonstrates two shipping use cases (main-engine anomaly-to-work-order and auxiliary-engine edge health model deployment).
Limitations
- No quantitative evaluation or benchmark comparison is provided.
- Demonstration-only; the LLM backbone used is not named in the text.
Experimental setup
Datasets: ship sensor and operational data domain knowledge graph
Builds on: LangGraph Open Horizon
Closest papers by meaning
- LLM-PySC2: Starcraft II learning environment for Large Language Models (NeurIPS 2025 · similarity 0.85)
- Multi-agent Architecture Search via Agentic Supernet (ICML 2025 · similarity 0.85)
- Fleet of Agents: Coordinated Problem Solving with Large Language Models (ICML 2025 · similarity 0.85)
- Agentick: A Unified Benchmark for General Sequential Decision-Making Agents (NeurIPS 2026 · similarity 0.84)
- AgentSwift: Efficient LLM Agent Design via Value-Guided Hierarchical Search (AAAI 2026 · similarity 0.84)
- DyFlow: Dynamic Workflow Framework for Agentic Reasoning (NeurIPS 2025 · similarity 0.84)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.