Darwin-Gödel Self-Rewrite
An agent rewrites its own code across generations, archives every successful variant, and samples parents from the archive for diversity — escaping the local optima that greedy self-rewrite hits.
Intent & Description
🎯 Intent
Let the agent self-improve over many generations without getting stuck on the first plateau it finds.
📋 Context
You’re running a research agent that can read and rewrite parts of its own implementation. Greedy self-rewrite — always mutating from the current best — has plateaued. You have a benchmark to score variants and want the agent to keep improving without human edits.
💡 Solution
Maintain a versioned archive of self-modifications. Each generation: (1) sample a parent from the archive using a diversity-aware policy (not strictly the best); (2) propose a mutation; (3) run a viability gate (compiles, passes safety checks, smoke test); (4) score on the objective; (5) add viable variants to the archive with score and lineage. Sampling from the archive — not just the current best — lets low-scoring but novel variants become parents of future high-scoring ones.
Real-world Use Case
- The agent can safely rewrite its own implementation (code, prompt, scaffolding).
- A clear objective score is available per variant.
- Greedy self-rewrite has empirically plateaued.
Source
📌 TL;DR
Self-rewrite + archive + diversity sampling = evolutionary search over agent implementations. Escapes local optima. Audit trail included. Safety gate required.
Advantages
- Escapes local optima that greedy self-rewrite can’t get past.
- Archive preserves lineage, making regressions debuggable.
- Diversity-weighted sampling reuses old branches as stepping-stones.
- Viability gate keeps the archive populated with runnable variants only.
Disadvantages
- Archive storage and bookkeeping grows with generations.
- Diversity metric is a design choice — a bad one biases the search wrong.
- Viability gate is a single point of failure; a bug there lets broken variants in.
- Self-modifying agents are inherently harder to audit and safety-check.