Search papers, labs, and topics across Lattice.
This paper introduces Design-to-Plan, a multi-agent framework leveraging large language models (LLMs) for comprehensive manufacturing process planning from 3D CAD models and 2D engineering drawings. By orchestrating specialized agents for tasks such as feature recognition and tool selection, the framework enables end-to-end reasoning that integrates various design artifacts and domain-specific rules. The evaluation demonstrates a 100% success rate across downstream agents and significant improvements in accuracy and efficiency, highlighting the framework's potential to automate and streamline manufacturing planning processes.
A structured LLM-based multi-agent system achieves 100% success in manufacturing process planning, transforming how design artifacts are interpreted into actionable plans.
Manufacturing process planning transforms heterogeneous design information into coherent manufacturing decisions. However, existing approaches focus on isolated subtasks, such as feature recognition, drawing interpretation, or tool selection, and struggle to support the full reasoning chain from design artifacts to process plans. This is critical when planning must interpret 3D CAD models, 2D engineering drawings, materials, and domain-specific rules. To address this gap, this paper presents Design-to-Plan, a large language model (LLM)-based multi-agent framework for end-to-end manufacturing process planning. An orchestrator coordinates specialized agents for 3D feature recognition, 2D drawing analysis, 2D-3D context fusion, knowledge retrieval, process sequencing, tool selection, and report generation. Rather than using LLMs as standalone text generators, the framework deploys them as reasoning agents that interact with deterministic modules and knowledge sources to produce consistent and traceable decisions. In this hybrid design, deterministic modules and specialized agents extract structured information from CAD and drawing inputs, while LLM agents perform context-aware reasoning, retrieve manufacturing rules, resolve conflicts, and generate planning outputs. The framework is evaluated using 300 benchmark cases across three downstream ReAct-enabled agents, plus separate evaluations of CAD feature recognition, drawing analysis, and 2D-3D context fusion. The parallel architecture achieves 100% success across downstream agents, Tool F1 scores of 95.9%-97.6%, 90% source detection accuracy in conflict analysis, and a 60%-68% reduction in token usage for key planning tasks. Results show that structured LLM-based multi-agent coordination can bridge design representations and manufacturing knowledge, enabling scalable, efficient, and traceable design-to-plan automation.
