{"ID":2900839,"CreatedAt":"2026-06-01T05:51:17.9442275Z","UpdatedAt":"2026-06-01T06:23:29.641557848Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2605.30889","arxiv_id":"2605.30889","title":"MLIPilot: LLM-Driven Auto-Research for Machine-Learned Interatomic Potentials","abstract":"Constructing production-quality machine-learned interatomic potentials (MLIPs) requires balancing accuracy, dynamical stability, and computational throughput under constraints that are not captured by a single training loss. We introduce MLIPilot, an auto-research framework in which tool-calling large language models propose hypotheses, edit MLIP training code, launch HPC jobs, and accept or revert changes using a fixed, physically constrained scorecard. We evaluate MLIPilot on MACE potential optimization using both commercial and open-weight LLM agents, including GPT-5.5, GPT-4.1, Mistral-24B, and Qwen3-32B. The benchmarks span molecular and periodic settings: a QM7-derived dataset for which we generated B3LYP/6-31G(d) energies and forces, and a Cu EMT dataset with periodic copper supercells labeled by ASE's Effective Medium Theory calculator. Across these benchmarks, the strongest agents move initially constraint-violating baselines to accepted models by discovering useful training strategies, including output normalization, loss-function changes, progressive training schedules, and model-capacity adjustments. These results suggest that LLM agents can serve as autonomous operators for scientific machine-learning workflows when their search is constrained by domain-specific validation criteria, shifting part of MLIP development from manual trial-and-error toward auditable, automated experimentation.","short_abstract":"Constructing production-quality machine-learned interatomic potentials (MLIPs) requires balancing accuracy, dynamical stability, and computational throughput under constraints that are not captured by a single training loss. We introduce MLIPilot, an auto-research framework in which tool-calling large language models p...","url_abs":"https://arxiv.org/abs/2605.30889","url_pdf":"https://arxiv.org/pdf/2605.30889v1","authors":"[\"Etinosa Osaro\",\"Santosh Adhikari\",\"Stamatia Zavitsanou\",\"Kelsey Parker\",\"Dario Rocca\"]","published":"2026-05-29T06:25:47Z","proceeding":"physics.chem-ph","tasks":"[\"physics.chem-ph\",\"cs.LG\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}