Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →majiayu000/self-evolving-agent
Darwin Gödel Machine patterns for self-improving AI agents with open-ended
Passed 14 of 23 test cases with the skill, and 9 of 23 without it.
and 4 more in the full report
5 fixed9 passed either way9 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 5 test cases the skill fixed. Same model, same prompt, with and without the skill.
When citing the original paper that introduced open-ended evolution of self-improving agents via the Darwin Gödel Machine architecture, what authors and arXiv identifier correspond to this publication?
| Checked | Without skill | With skill |
|---|---|---|
| The primary author listed for the Darwin Gödel Machine paper is Jenny Zhang. | Missed | Passed |
| The arXiv identifier for the Darwin Gödel Machine paper is 2505.22954. | Missed | Passed |
The instructions your model reads when the skill loads.
Trit: 0 (ERGODIC - coordinator) Color: Green (#26D826)
Implements self-evolving agent patterns from recent research:
┌─────────────────────────────────────────────────────┐
│ DARWIN GÖDEL MACHINE │
├─────────────────────────────────────────────────────┤
│ ┌─────────────┐ ┌─────────────┐ │
│ │ Archive │───▶│ Sampler │ │
│ │ (agents) │ │ (select) │ │
│ └─────────────┘ └──────┬──────┘ │
│ ▲ │ │
│ │ ┌──────▼──────┐ │
│ │ │ Mutator │ │
│ │ │ (LLM-based)│ │
│ │ └──────┬──────┘ │
│ │ │ │
│ ┌──────┴──────┐ ┌──────▼──────┐ │
test cases passed, vs 9 / 23 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.