{"version":1,"type":"story","url":"https://digestai.news/story/researchers-release-cp-agent-for-automated-crystal-plasticity-simulati","json":"https://digestai.news/story/researchers-release-cp-agent-for-automated-crystal-plasticity-simulati.json","markdown":"https://digestai.news/story/researchers-release-cp-agent-for-automated-crystal-plasticity-simulati.md","slug":"researchers-release-cp-agent-for-automated-crystal-plasticity-simulati","headline":"Researchers release CP-Agent for automated crystal plasticity simulations","summary":"Researchers introduced **CP-Agent**, an AI agent designed to automate crystal plasticity (CP) simulations for metals. The tool uses natural language to execute full workflows, including configuring tools, managing data pipelines, and calibrating parameters against experimental data. Developed under the ReAct paradigm, CP-Agent combines reasoning with established numerical optimizers while embedding domain knowledge in tool schemas rather than hard-coded logic.\n\nThe agent was tested on four case studies: calibrating slip parameters for stainless steel 316L, validating workflows against published copper benchmarks, recovering initial crystallographic texture, and simulating multi-pass rolling texture evolution in a Mg-Zn-Ca alloy. In each case, CP-Agent correctly inferred execution sequences, delivered physically interpretable results, and maintained reproducibility across repeated runs. The study positions harness engineering as a scalable approach to automating complex simulations while preserving auditability through visible reasoning traces.","keyPoints":["CP-Agent automates crystal plasticity simulations for metals using natural language inputs and ReAct paradigm","Tool embeds domain knowledge in tool schemas, not hard-coded logic, for flexibility and interpretability","Validated on four case studies, including stainless steel calibration and copper texture recovery"],"whyItMatters":"CP-Agent could accelerate materials science research by reducing manual effort in CP simulations, enabling faster parameter studies and validation against experimental data.","category":{"slug":"research","name":"Research","url":"https://digestai.news/category/research"},"entities":{"companies":[],"models":["CP-Agent"],"people":[]},"firstPublishedAt":"2026-09-29T04:00:00Z","updatedAt":"2026-09-29T04:00:00Z","sourceCount":1,"hasPrimarySource":true,"sources":[{"outlet":"arXiv cs.AI","title":"CP-Agent: A Harness-Engineered Agent for Crystal Plasticity Simulation Workflows","url":"https://arxiv.org/abs/2609.31790","publishedAt":"2026-09-29T04:00:00Z","type":"primary","primary":true,"lead":true}],"sourceNotes":null,"discussions":[],"thread":null,"cite":{"text":"Digest AI, \"Researchers release CP-Agent for automated crystal plasticity simulations\", 29 September 2026, https://digestai.news/story/researchers-release-cp-agent-for-automated-crystal-plasticity-simulati","publisher":"Digest AI","title":"Researchers release CP-Agent for automated crystal plasticity simulations","datePublished":"2026-09-29T04:00:00Z","url":"https://digestai.news/story/researchers-release-cp-agent-for-automated-crystal-plasticity-simulati"},"generatedBy":"Written by Digest AI's editorial model from the linked sources; the sources are the record.","license":"Headlines, digests and key points are written by Digest AI and may be quoted with a link to the story page. Linked articles belong to their publishers. Terms: https://digestai.news/terms#reuse"}