Answers are grounded in this paper and cite their sources.
Reasoning models (LLMs) were used as optimisers for a 10-D chemistry problem and a 7-D physics simulation. The best performance was achieved using iterative closed-loop reasoning with a batch size of one.
No takes yet. Share an insight, caveat, or question.
Cisse et al. (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: