Evosearch
Run the CaP Fix Loop + Evolutionary Search experiment on a user-supplied list of...
Install
npx skills add NVlabs/ASPIRE --skill evosearch -g -a claude-code -y- Repository
- NVlabs/ASPIRE925
- Category
- Engineering
- Updated
- 20d ago
- License
- Apache-2.0
- Context cost
- Lightabout 713 tokens
- Runs scripts
- Yes, review before use
What it does
Run the CaP Fix Loop + Evolutionary Search experiment on a user-supplied list of low-performing benchmark tasks: iterative K=8 candidate search on development seeds 51, 65, validation selection, and final held-out evaluation on seeds 1, 50.
Fix Loop + Evolutionary Search
Use this skill for intensive debugging of difficult tasks, Evolutionary Search's
multi-candidate search finds strategies the single-pass fix loop misses. It builds on the
iterative-debugging skill: each task's fix loop fix_code.py (when present) is the baseline
to beat, seeded verbatim as candidate_A. LIBERO-Pro runs use --init-mode seeded so
development seeds 51, 65 and held-out seeds 1, 50 are distinct scenes.
Setup
- Complete benchmark setup for the target embodiment (
docs/libero-pro.md, ordocs/robosuite.md), including the pinned environment (for LIBERO:scripts/bootstrap_libero.sh→.venv-libero) and SAM3 authentication. - Export the benchmark environment variables (for LIBERO:
LIBERO_CONFIG_PATH="$PWD/.libero",MUJOCO_GL=egl,PYOPENGL_PLATFORM=egl,EGL_PLATFORM=device,TORCH_FORCE_NO_WEIGHTS_ONLY_LOAD=1). - Start perception services (
scripts/supervise_services.sh) and a persistent coordinator session. - Confirm the Fix Loop experiment has produced
fix_code.py(and a baseline held-out rate) for the target tasks when available. - Read
docs/api-reference.md,docs/run-artifacts.md, and main-agent-prompt.md.
