Libero Fix Loop

Run the baseline-free LIBERO-Pro Fix Loop: inspect one initial observed scene, generate task-level code, debug failures on seeds 51–65 using traces and keyframes, validate on seeds 1–50, and promote reusable patterns.

nvlabs 9fa3052 7 files · 31.0 KB Updated

File contents

LIBERO Fix Loop

Use this skill for Experiment 1. Start with INSTRUCTIONS.md.

Run Order

  1. Follow main-agent-prompt.md as coordinator.
  2. Fill subagent-prompt.md once per task.
  3. Each worker follows skills/task-exploration.md, generates its own initial code, then uses the original failure-by-failure debug loop.
  4. Use clean-task-slate.md before reruns.
  5. Promote Stage 1-supported patterns into ../skills/ and record each update with scripts/libero/record_skill_promotion.py before dispatching the next Stage 1 task. Held-out outcomes never drive skill edits.

No external baseline code or baseline output directory is used.

nvlabs/aspire/tree/main/aspire/sim/.claude/libero/fix-loop commit 9fa3052520

Frequently asked questions

npx skillmds@latest add nvlabs/libero-fix-loop