CP-Agent: an LLM agent that runs crystal plasticity simulation workflows from natural language
Fowe · x · 2026-10-03
Crystal plasticity (CP) simulations are key to predicting polycrystalline metal behavior, but manual tool setup, data pipelines, and parameter calibration slow routine use. Researchers present CP-Agent, a harness-engineered LLM agent that runs complete CP workflows from natural-language tasks:
- Built on the ReAct paradigm, reasoning about tool selection and sequencing
- Delegates numerical search to optimizers
- Encodes domain knowledge through tool schemas instead of hard-coded logic
Preprint available on arXiv, demonstrating how LLM agents can automate scientific simulation workflows.
More from coding & agent
- Claude helps build an entire manufacturing line in Blender, down to probe card needles — jwt0625 · 2026-10-03
- Jevbox: open-source self-organizing document drive with hierarchical search, no vector DB — rickasaurus · 2026-10-03
- AI will write 748 tests — except they are all the wrong ones — chrisalbon · 2026-10-03
- After two years building agent memory continuity, the same Opus follows him everywhere — RileyRalmuto · 2026-10-03
- Fireworks launches cache-aware FireRouter with Opus: coding costs cut 57% at 98% accuracy — Madisonkanna · 2026-10-03
- MegaCapybara: RTX 5090-only inference engine hits 2000+ t/s, 2x faster than Ninfer — BringTea_666 · 2026-10-03