Agentic Additive Manufacturing Alloy Discovery

2025-10-02

AI Summary

Efficient discovery of printable alloys in additive manufacturing (AM) faces challenges including multidisciplinary coupling, high experimental costs, and lengthy trial-and-error cycles. To address these, this work proposes a large language model (LLM)-driven multi-agent system that integrates computational thermodynamics (Thermo-Calc), melt-pool defect modeling, and the Model Context Protocol (MCP) for tool orchestration—enabling autonomous reasoning and dynamic task planning tailored to printability prediction. The system supports iterative refinement of analytical pathways based on real-time computational outputs, achieving an end-to-end closed loop spanning alloy composition design, phase diagram analysis, and defect risk assessment. Experimental evaluation demonstrates over 60% reduction in alloy screening time, significantly enhancing both innovation and feasibility validation efficiency for novel alloy candidates. This approach establishes a scalable, data- and knowledge-driven paradigm for AM materials development.

Technology Category

• Cognitive Modeling & Cognitive Systems: Computational Creativity
• Machine Learning: Large Multimodal Models (LMMs)
• Planning, Routing, and Scheduling: Planning with Language Models

Application Category

• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation

Abstract

Agentic systems enable the intelligent use of research tooling, augmenting a researcher's ability to investigate and propose novel solutions to existing problems. Within Additive Manufacturing (AM), alloy discovery remains a complex challenge, often requiring expertise in the various domains of materials science, thermodynamic simulations, and experimental analysis. Large Language Model (LLM) enabled agents can facilitate this endeavor by utilizing their extensive knowledge base to dispatch tool calls via Model Context Protocol (MCP) to perform actions such as Thermo-Calc property diagram calculations and lack of fusion process map generation. In addition, the multi-agent system developed in this work is able to effectively reason through complex user prompts and provide analysis on the printability of proposed alloys. These agents can dynamically adjust their task trajectory to the outcomes of tool call results, effectively enabling autonomous decision-making in practical environments. This work aims to utilize LLM enabled agents to automate and accelerate the task of alloy discovery within the field of additive manufacturing and showcase the benefits of adopting this multi-agent system.

Problem

• Automating alloy discovery process in additive manufacturing
• Using multi-agent systems to analyze alloy printability
• Accelerating materials research through autonomous decision-making agents

Innovation

• LLM agents automate alloy discovery via tool calls
• Multi-agent system dynamically adjusts task trajectory
• Agents analyze alloy printability using thermodynamic simulations