AGENT SKILL

proxy_training_recovery

Run a bounded Moderate-DS proxy recovery harness with generated skill invocations and optimizer evidence.

License 许可
Apache-2.0
最近更新
2026-09-03
Stars
★ 351
Forks
27

01 前言 Front Matter

name
proxy_training_recovery
description
Run a bounded Moderate-DS proxy recovery harness with generated skill invocations and optimizer evidence.

02 资源文件 2

03 SKILL.md 正文

Proxy Training Recovery Harness

Use this skill when full image-dataset retraining is blocked but soft-mode recovery permits a declared mechanism-faithful proxy. The harness must import or call the scoring, median-selection, and ablation skills, produce executable logs, and write validator-compatible recovery artifacts.

Inputs

  • Attempt directory containing module_plan.json and environment/runtime_handoff.json.
  • Generated skills root containing the Moderate-DS module skills.
  • Optional synthetic dataset parameters for stress tests.

Outputs

  • recovery/recovery_result.json with numeric metrics and mechanism checks.
  • recovery/logs/generated_data_item.json describing the proxy data.
  • recovery/logs/training_trace.json showing loss before and after a real optimizer update.
  • recovery/logs/generated_skill_invocations.json proving all core skills were exercised.

Workflow

  1. Create a deterministic class-cluster representation dataset with central, moderate, and far points.
  2. Import the generated scoring, median-selection, and ablation scripts from the generated skills root.
  3. Select the moderate coreset and compare it against extreme policies.
  4. Run a simple trainable linear proxy update on the selected coreset and log parameter changes.
  5. Write recovery artifacts and source boundaries before invoking validation.

Validation

Run python scripts/run_proxy_recovery.py --attempt-dir <attempt_dir> --skills-root <skills_root>. Then run the Distiller recovery validator on the attempt directory.

Limitations

This is not a full CIFAR-100/ImageNet reproduction. It is a soft-mode proxy that validates the mechanism under bounded runtime constraints.

04 同仓库更多 Skills

VectorSpaceLab
VectorSpaceLab/AREX-Skill

passnet-triton-opt

Make a single PassNet Triton kernel fast AND numerically faithful: performance model (when a replacement can win at all), block/grid/warp tuning, autotune policy, launch overhead, and per-op numeric recipes to pass the dtype baseline tolerances. Use when a pass matches and is correct but speedup below expected, or when correctness fails by small numeric margins.

★ 351
VectorSpaceLab
VectorSpaceLab/AREX-Skill

passnet-solve

END-TO-END playbook for solving one PassNet sample: analyze the computation graphs, decide the optimization strategy (what to fuse, what to replace, what to leave alone), drive the iteration loop, and maximize the sample score. This is the ENTRY skill — invoke it first for any PassNet optimization task; it tells you when to use passnet-pattern-fusion, passnet-triton-opt and passnet-feedback.

★ 351
VectorSpaceLab
VectorSpaceLab/AREX-Skill

passnet-skill

PassNet GPU kernel optimization via compiler passes. Design and implement Triton-based optimization passes, create pass files under ./pass_dir/, self-evaluate with pass_evaluator, and iterate to maximize GPU speedup.

★ 351
VectorSpaceLab
VectorSpaceLab/AREX-Skill

passnet-pattern-fusion

Author PassNet pass files: write patterns that actually MATCH the FX graph, pick fusion regions (which ops to absorb into one Triton kernel), and structure multi-pass submissions with the mandatory shared-dispatch architecture. Use when creating or fixing pattern()/replacement_args()/replacement_func() files, when a pass "failed to match", or when deciding how to fuse multiple kernels/ops.

★ 351
VectorSpaceLab
VectorSpaceLab/AREX-Skill

passnet-orchestrate

Round/batch planning and decision support for PassNet graph optimization. Use for multi-sample triage, worker allocation, eval-budget policy, and post-eval keep/revert decisions. For solving one concrete sample end to end, use passnet-solve as the entry skill; consult this skill only when you need broader planning or a specific decision gate.

★ 351
VectorSpaceLab
VectorSpaceLab/AREX-Skill

passnet-feedback

Fast, deterministic feedback for PassNet work: pre-flight pattern/match verification WITHOUT burning a GPU evaluation, per-node bottleneck analysis of a sample's graphs, and eval-log parsing into per-variant status + estimated score + failure classification. Use BEFORE every GPU evaluation (check_pattern), at the START of a sample (analyze_graph), and AFTER every evaluation (parse_eval_log).

★ 351