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

• URL: http://arxiv.org/abs/2604.05547v1
• Date: Tue, 07 Apr 2026 07:45:17 GMT
• Title: COSMO-Agent: Tool-Augmented Agent for Closed-loop Optimization,Simulation,and Modeling Orchestration
• Abstract summary: COSMO-Agent is a tool-augmented reinforcement learning framework that teaches LLMs to complete the closed-loop CAD-CAE process.<n>We design a multi-constraint parametric reward that jointly encourages feasibility, toolchain robustness, and structured output validity.<n>Experiments show that COSMO-Agent training substantially improves small open-source LLMs for constraint-driven design.
• Score: 26.690772733565996
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: 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.

Related papers

• Embodied CAD: Solver-Grounded LLM Agents for Parametric B-Rep Assembly Modeling [7.918861077775763]
  We present Embodied CAD, solver-grounded LLM agents for parametric B-Rep assembly modeling.<n>The framework combines action grammar constraints, deterministic parameter resolution, and solver-derived rewards for supervised warm-up and GRPO-style refinement.<n>We evaluate Embodied CAD on multi-step mechanical, industrial equipment, and mold-oriented assembly tasks using solver-aligned metrics.
  arXiv  Detail & Related papers  (2026-06-30T07:31:01Z)
• IterCAD: An Iterative Multimodal Agent for Visually-Grounded CAD Generation and Editing [31.86100517851177]
  IterCAD is a unified multimodal agent framework for closed-loop, interactive CAD generation and editing.<n>It achieves highly competitive performance across multiple benchmarks, significantly outperforming existing approaches in both code executability and geometric precision.
  arXiv  Detail & Related papers  (2026-06-11T13:53:21Z)
• Tool-Augmented Agent for Closed-loop Optimization,Simulation,and Modeling Orchestration [26.690772733565996]
  COSMO-Agent is a tool-augmented reinforcement learning framework that teaches LLMs to complete the closed-loop CAD-CAE process.<n>We design a multi-constraint parametric reward that jointly encourages feasibility, toolchain robustness, and structured output validity.<n>Experiments show that COSMO-Agent training substantially improves small open-source LLMs for constraint-driven design.
  arXiv  Detail & Related papers  (2026-04-01T14:14:09Z)
• Execution-Verified Reinforcement Learning for Optimization Modeling [49.171122807323634]
  Execution-verified learning framework treats a mathematical programming solver as a deterministic, interactive verifier.<n>Experiments on NL4OPT, MAMO, IndustryOR, and OptiBench across Gurobi, OR-Tools, and COPT show that EVOM matches or outperforms process-supervised SFT.
  arXiv  Detail & Related papers  (2026-04-01T03:39:11Z)
• Let It Flow: Agentic Crafting on Rock and Roll, Building the ROME Model within an Open Agentic Learning Ecosystem [90.17610617854247]
  We introduce the Agentic Learning Ecosystem (ALE), a foundational infrastructure that optimize the production pipeline for agentic model.<n>ALE consists of three components: ROLL, a post-training framework for weight optimization; ROCK, a sandbox environment manager for trajectory generation; and iFlow CLI, an agent framework for efficient context engineering.<n>We release ROME, an open-source agent grounded by ALE and trained on over one million trajectories.
  arXiv  Detail & Related papers  (2025-12-31T14:03:39Z)
• CME-CAD: Heterogeneous Collaborative Multi-Expert Reinforcement Learning for CAD Code Generation [30.08737988265254]
  Existing methods that reconstruct 3D models from sketches often produce non-editable and approximate models.<n>We propose the Heterogeneous Collaborative Multi-Expert Reinforcement Learning (CME-CAD) paradigm, a novel training paradigm for CAD code generation.<n>We introduce a two-stage training process: Multi-Expert Fine-Tuning (MEFT), and Multi-Expert Reinforcement Learning (MERL)
  arXiv  Detail & Related papers  (2025-12-29T09:37:53Z)
• Sample-Efficient Online Learning in LM Agents via Hindsight Trajectory Rewriting [92.57796055887995]
  We introduce ECHO, a prompting framework that adapts hindsight experience replay from reinforcement learning for language model agents.<n> ECHO generates optimized trajectories for alternative goals that could have been achieved during failed attempts.<n>We evaluate ECHO on stateful versions of XMiniGrid, a text-based navigation and planning benchmark, and PeopleJoinQA, a collaborative information-gathering enterprise simulation.
  arXiv  Detail & Related papers  (2025-10-11T18:11:09Z)
• From Intent to Execution: Multimodal Chain-of-Thought Reinforcement Learning for Precise CAD Code Generation [47.67703214044401]
  We propose CAD-RL, a multimodal Chain-of-Thought guided reinforcement learning framework for CAD modeling code generation.<n>Our method combines Cold Start with goal-driven reinforcement learning post training using three task-specific rewards.<n>Experiments demonstrate that CAD-RL achieves significant improvements in reasoning quality, output precision, and code executability.
  arXiv  Detail & Related papers  (2025-08-13T18:30:49Z)
• Feedback-Driven Tool-Use Improvements in Large Language Models via Automated Build Environments [70.42705564227548]
  We propose an automated environment construction pipeline for large language models (LLMs)<n>This enables the creation of high-quality training environments that provide detailed and measurable feedback without relying on external tools.<n>We also introduce a verifiable reward mechanism that evaluates both the precision of tool use and the completeness of task execution.
  arXiv  Detail & Related papers  (2025-08-12T09:45:19Z)
• Generative AI for CAD Automation: Leveraging Large Language Models for 3D Modelling [31.94035963354055]
  Large Language Models (LLMs) are revolutionizing industries by enhancing efficiency, scalability, and innovation.<n>This paper investigates the potential of LLMs in automating Computer-Aided Design (CAD) by integrating FreeCAD with LLM as CAD design tool.<n>We propose a framework where LLMs generate initial CAD scripts from natural language descriptions, which are then executed and refined iteratively based on error feedback.
  arXiv  Detail & Related papers  (2025-07-05T23:30:17Z)
• MLE-Dojo: Interactive Environments for Empowering LLM Agents in Machine Learning Engineering [57.156093929365255]
  Gym-style framework for systematically reinforcement learning, evaluating, and improving autonomous large language model (LLM) agents.<n>MLE-Dojo covers diverse, open-ended MLE tasks carefully curated to reflect realistic engineering scenarios.<n>Its fully executable environment supports comprehensive agent training via both supervised fine-tuning and reinforcement learning.
  arXiv  Detail & Related papers  (2025-05-12T17:35:43Z)
• BlenderLLM: Training Large Language Models for Computer-Aided Design with Self-improvement [45.19076032719869]
  We present BlenderLLM, a framework for training Large Language Models (LLMs) in Computer-Aided Design (CAD)<n>Our results reveal that existing models demonstrate significant limitations in generating accurate CAD scripts.<n>Through minimal instruction-based fine-tuning and iterative self-improvement, BlenderLLM significantly surpasses these models in both functionality and accuracy of CAD script generation.
  arXiv  Detail & Related papers  (2024-12-16T14:34:02Z)

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.