nvlabs LIBERO Fix Loop + Evolutionary Search
Use this skill for Experiment 2. Start with INSTRUCTIONS.md.
Run Order
- Start with INSTRUCTIONS.md.
- Confirm the Fix Loop experiment has produced
fix_code.pyfor the target tasks. - Follow main-agent-prompt.md as the coordinator.
- Fill subagent-prompt.md once per task below the success threshold and dispatch subagents on the available worker GPUs.
- Read experiment-specific companion skills under skills/ when generating candidates.
- Use clean-task-slate.md before rerunning a task or suite.
Files
| File | Purpose |
|---|---|
| INSTRUCTIONS.md | End-to-end human/agent entrypoint |
| main-agent-prompt.md | Coordinator runbook for Evolutionary Search task dispatch and result collection |
| subagent-prompt.md | Per-task Evolutionary Search iteration prompt |
| clean-task-slate.md | Reset checklist before reruns |
| skills/evosearch-iteration.md | Candidate/eval/keyframe iteration mechanics |
| ../api-reference.md | LIBERO reduced API reference |
| ../skills/ | Shared LIBERO robot skills |