mlsanityData to 7 Oct 2026

A Multi-Agent Framework for Zero-Dimensional Reduced-Order Model Planning

arXiv 2607.10994 ↗First posted 13 Jul 2026cs.LGcited by 0

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

Abstract (arXiv)

Zero-dimensional reduced-order models (0D ROMs) are central to multi-dimensional design workflows for high-end complex equipment. However, the planning process currently relies on manual expertise, limiting topological exploration and prolonging iterations. Even traditional optimization methods such as Genetic Algorithms (GA) are typically confined to local parameter tuning. Although Large Language Model (LLM) agents have shown promise in exploring large sample spaces, and frameworks such as Chain of Thought (CoT) and Reason and Act (ReAct) improve reasoning reliability, while Retrieval-Augmented Generation (RAG) overcomes domain knowledge barriers, a single agent still falls short for the long-horizon and highly coupled nature of complex 0D ROM planning. This paper proposes the Zero-dimensional reduced-order model CO-Planning framework (Z-COPA), a multi-agent architecture featuring a Symbolic Action Graph Engine (SAGE) and a MILP-Guided Navigation (MGN) optimizer. Its core innovation is a dedicated graph representation method that accurately encodes the 0D flow network topology, converting the empirical planning process into a rigorous graph structure optimization problem. We validate the forward and inverse design capabilities and generalization performance of Z-COPA on two real aircraft engine secondary-air systems, two IEEE power-distribution reconfiguration benchmarks, and two water-distribution network benchmarks. The results show superior task completion quality, obtaining the best performance in both forward and reverse design of air systems. Z-COPA disrupts the traditional 0D model planning paradigm, providing a new technical approach for exploring broader topological space and achieving highly automated, globally optimal air system architectures.

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 45 references that are in the map. First posted on arXiv 13 Jul 2026.

Builds on

18 of 45 references.

Closest ancestors · 2

Same direction, newest first

  1. 2023MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework1 Aug
  2. 2023CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society31 Mar

Other references · 16

  1. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  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. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,064
  5. 2023A Survey of Large Language Modelscited by 2,537
  6. 2023AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversationcited by 1,906
  7. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,800
  8. 2024From Local to Global: A Graph RAG Approach to Query-Focused Summarizationcited by 1,411
  9. 2023Eureka: Human-Level Reward Design via Coding Large Language Modelscited by 542
  10. 2024From human experts to machines: An LLM supported approach to ontology and knowledge graph constructioncited by 40
  11. 2023Plan, Eliminate, and Track -- Language Models are Good Teachers for Embodied Agentscited by 32
  12. 2025SciSciGPT: Advancing Human-AI Collaboration in the Science of Sciencecited by 26
4 more
  1. 2025Hyper-RAG: Combating LLM Hallucinations using Hypergraph-Driven Retrieval-Augmented Generationcited by 23
  2. 2025Ontology-Guided Reverse Thinking Makes Large Language Models Stronger on Knowledge Graph Question Answeringcited by 15
  3. 2025SimulRAG: Simulator-based RAG for Grounding LLMs in Long-form Scientific QAcited by 3
  4. 2025Data-Driven Bifurcation Handling in Physics-Based Reduced-Order Vascular Hemodynamic Modelscited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026PathWise: Planning through World Model for Automated Heuristic Design via Self-Evolving LLMs
  2. 2025A Multidisciplinary Design and Optimization (MDO) Agent Driven by Large Language Models
  3. 2025Large Language Models for Combinatorial Optimization of Design Structure Matrix
  4. 2026Design-to-Plan: A Large Language Model-Based Multi-Agent Framework for Manufacturing Process Planning from 3D CAD Models and 2D Engineering Drawings
  5. 2025Agentic Large Language Models for Conceptual Systems Engineering and Design
  6. 2026Co-evolving Agent Architectures and Interpretable Reasoning for Automated Optimization
  7. 2025Knowledge Graph Fusion with Large Language Models for Accurate, Explainable Manufacturing Process Planning
  8. 2025Hierarchical Planning for Complex Tasks with Knowledge Graph-RAG and Symbolic Verification