Run multi-start
run_multistartRun multi-start optimization by sampling designs with LHS, keeping the top feasible seeds, then locally optimizing each seed, optionally across parallel workers.
Instructions
Multi-start optimization: LHS sampling, keep the top_k feasible seeds, then a normalized local optimization (SLSQP by default) from each, in spawn worker processes when n_workers > 1.
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"problem_id": "<problem_id>",
"n_samples": "<n_samples>",
"top_k": "<top_k>"
},
"name": "run_multistart"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| seed | No | ||
| top_k | Yes | ||
| n_samples | Yes | ||
| n_workers | No | ||
| optimizer | No | ||
| problem_id | Yes | ||
| auto_normalize | No | ||
| feasibility_tol | No |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
| best | No | ||
| runs | No | ||
| error | No | ||
| messages | No | ||
| n_sampled | No | ||
| captured_output | No | ||
| n_feasible_seeds | No | ||
| doe_recorder_path | No |