Track synthesis, materials and catalysis as it is published.
Search papers, labs, and topics across Lattice.
The authors construct CP-Agent, a ReAct-based agent framework that autonomously orchestrates end-to-end crystal plasticity simulation pipelines directly from natural language specifications. Automating these multi-scale materials modeling workflows addresses a longstanding bottleneck in computational mechanics, where heterogeneous tool configurations and iterative experimental calibration require high manual overhead. Across four experimental benchmarks—including 316L stainless steel parameter calibration and a 5-pass deformation rolling sequence of an Mg-Zn-Ca alloy—the agent successfully synthesized correct tool execution graphs, delegated continuous parameter search to external optimizers, and reproduced subtle physical phenomena such as split basal texture evolution.
Shifting domain physics into typed tool schemas enables off-the-shelf LLMs to autonomously solve complex inverse problems and multi-pass metallurgical simulations without specialized fine-tuning.
Crystal plasticity (CP) simulations predict the mechanical behavior of polycrystalline metals, yet their routine use is hindered by the manual effort of configuring heterogeneous tools, orchestrating multi-step data pipelines, and calibrating constitutive parameters against experiments. These bottlenecks impede productivity in systematic parameter studies, motivating interest in automated workflows. This study presents CP-Agent, a harness-engineered LLM-based agent that autonomously executes complete CP modeling workflows from natural-language tasks. Operating under the ReAct paradigm, the agent reasons about tool selection and sequencing while delegating numerical search to established optimizers. The harness comprises a minimal system prompt, typed tool definitions, a dispatcher, and a safety-bounded iteration loop, encoding domain knowledge through tool schemas rather than hard-coded logic. CP-Agent is demonstrated on four case studies: calibrating four slip parameters of additively manufactured stainless steel 316L against tensile data; validating the workflow against published copper benchmarks, reproducing stress-strain and texture evolution; recovering the initial crystallographic texture of copper, where the agent correctly identifies a diffuse initial texture; and reproducing the multi-pass rolling texture evolution of a Mg-Zn-Ca alloy, where the agent chains five deformation passes and recovers the experimentally observed weakened, split basal texture. In all cases, the agent inferred the correct execution sequence from the task statement, robustly across repeated runs, and delivered physically interpretable results. This work establishes harness engineering as a systematic approach to automating CP modeling workflows while maintaining physical interpretability and auditability through visible reasoning traces.