mlsanityData to 7 Oct 2026

COSMO-Agent: Tool-Augmented Agent for Closed-loop Optimization,Simulation,and Modeling Orchestration

arXiv 2604.05547 ↗First posted 7 Apr 2026cs.AI cs.GRcited by 2

On the map: LLM agents and tool use → Multimodal and embodied agents

Abstract (arXiv)

Iterative industrial design-simulation optimization is bottlenecked by the CAD-CAE semantic gap: translating simulation feedback into valid geometric edits under diverse, coupled constraints. To fill this gap, we propose COSMO-Agent (Closed-loop Optimization, Simulation, and Modeling Orchestration), a tool-augmented reinforcement learning (RL) framework that teaches LLMs to complete the closed-loop CAD-CAE process. Specifically, we cast CAD generation, CAE solving, result parsing, and geometry revision as an interactive RL environment, where an LLM learns to orchestrate external tools and revise parametric geometries until constraints are satisfied. To make this learning stable and industrially usable, we design a multi-constraint reward that jointly encourages feasibility, toolchain robustness, and structured output validity. In addition, we contribute an industry-aligned dataset that covers 25 component categories with executable CAD-CAE tasks to support realistic training and evaluation. Experiments show that COSMO-Agent training substantially improves small open-source LLMs for constraint-driven design, exceeding large open-source and strong closed-source models in feasibility, efficiency, and stability.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Placed in Multimodal and embodied agents, one of 16 directions in LLM agents and tool use. Builds on 20 of its 39 references that are in the map. First posted on arXiv 7 Apr 2026.

Builds on

20 of 39 references.

Closest ancestors · 1

Same direction, newest first

  1. 2025MooseAgent: A LLM Based Multi-agent Framework for Automating Moose Simulation11 Apr

Other references · 19

  1. 2022Training language models to follow instructions with human feedbackcited by 15,712
  2. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  3. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  4. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,072
  5. 2020Fourier Neural Operator for Parametric Partial Differential Equationscited by 2,806
  6. 2022Self-Instruct: Aligning Language Models with Self-Generated Instructionscited by 2,674
  7. 2022Do As I Can, Not As I Say: Grounding Language in Robotic Affordancescited by 2,302
  8. 2024HybridFlow: A Flexible and Efficient RLHF Frameworkcited by 1,980
  9. 2019DeepONet: Learning nonlinear operators for identifying differential equations based on the universal approximation theorem of operatorscited by 1,965
  10. 2023ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIscited by 1,880
  11. 2022MRKL Systems: A modular, neuro-symbolic architecture that combines large language models, external knowledge sources and discrete reasoningcited by 153
  12. 2021JoinABLe: Learning Bottom-up Assembly of Parametric CAD Jointscited by 77
7 more
  1. 2020SketchGraphs: A Large-Scale Dataset for Modeling Relational Geometry in Computer-Aided Designcited by 72
  2. 2025Text-to-CadQuery: A New Paradigm for CAD Generation with Scalable Large Model Capabilitiescited by 43
  3. 2024CAD-Assistant: Tool-Augmented VLLMs as Generic CAD Task Solverscited by 40
  4. 2024MetaOpenFOAM: an LLM-based multi-agent framework for CFDcited by 39
  5. 2024OpenECAD: An Efficient Visual Language Model for Editable 3D-CAD Designcited by 26
  6. 2025InternBootcamp: Boosting LLM Reasoning with Verifiable Task Scalingcited by 19
  7. 2025Fine-tuning a Large Language Model for Automating Computational Fluid Dynamics Simulationscited by 18

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026CADENA: Stepwise CAD Reverse Engineeringcited by 0
  2. 2026Large language models for partial differential equation workflowscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Tool-Augmented Agent for Closed-loop Optimization,Simulation,and Modeling Orchestration
  2. 2026TOOLCAD: Exploring Tool-Using Large Language Models in Text-to-CAD Generation with Reinforcement Learning
  3. 2025CME-CAD: Heterogeneous Collaborative Multi-Expert Reinforcement Learning for CAD Code Generation
  4. 2026Physics-in-the-Loop: A Hybrid Agentic Architecture for Validated CAD Engineering Design
  5. 2026Memory-Augmented Reinforcement Learning Agent for CAD Generation
  6. 2025From Intent to Execution: Multimodal Chain-of-Thought Reinforcement Learning for Precise CAD Code Generation
  7. 2025A Multidisciplinary Design and Optimization (MDO) Agent Driven by Large Language Models
  8. 2025cadrille: Multi-modal CAD Reconstruction with Reinforcement Learning