Evolution Lab Advanced 2 minute read Updated 2026-06-26 UTC

Mutation operators

A catalog of bounded transformations for models, adapters, routers, data recipes, and code—with risk and compatibility controls.

Research statusEstablished and emerging evolutionary/ML methods Publication statePublished Reviewed byMichael Kappel Source reports3

Mutation is a declared transformation

A mutation operator maps one or more parent packages to a descendant. Operators should be allowlisted, versioned, deterministic where possible, and constrained by explicit parameter ranges.

Model-level operators

OperatorBest useMain controls
Fine-tuneAdd or improve a narrow capabilityData lineage, regularization, forgetting tests
Adapter trainCheap specialization on a stable baseBase digest, adapter rank, interference tests
DistillCompress a teacher or coalitionTeacher quality, synthetic-data review, coverage
QuantizeReduce memory and latencyPer-slice regression, calibration, hardware profile
PruneRemove low-value parameters or expertsRare-case tests, sparsity support, rollback
Expert splitSeparate conflicting nichesRouter retraining, load balance, population cap
Prompt/system policy variantChange behavior without weightsVersioned prompt, injection tests, no policy bypass
Router threshold mutationChange selection behaviorTraffic simulation, fairness, exploration reserve

Code-level operators

Code-level changes require a separate trust path. Examples include AST patching, algorithm replacement, kernel configuration, cache policy, batching, or workflow graph edits. The operator output must pass compilation, tests, static analysis, security scanning, determinism checks, and performance profiling.

Mutation budget

pseudocode
mutation_budget <- {
    max_candidates: 24,
    max_training_gpu_hours: 40,
    max_data_examples: 500000,
    allowed_operators: ["adapter_train", "quantize", "router_threshold"],
    max_parameter_delta_norm: 0.15,
    max_permission_delta: NONE,
    max_wall_clock_hours: 12,
    maximum_descendant_depth: 8
}

Adaptive mutation rates

Mutation strength can respond to evidence: increase exploration after stagnation, decrease it after instability, or target failure clusters. Adaptation itself must be bounded and logged. Do not let a candidate choose its own mutation rate based on access to hidden evaluation results.

Validity before fitness

Many mutations produce invalid artifacts. Run cheap validity gates first: package integrity, load test, contract schema, basic sanity, and resource ceiling. Reserve expensive evaluations for candidates that satisfy these prerequisites.

One family at a time

For scientific clarity, begin with one operator family. If an adapter, quantization, router, and prompt all change at once, attribution is weak. Later factorial designs can test interactions explicitly.

Mutation operator scorecard

Evaluate operators by useful-descendant yield, average improvement, diversity contribution, cost, failure rate, reproducibility, and maintenance burden. An operator that occasionally finds a large win but produces many unsafe artifacts may not be viable in routine operation.

Source reports used for this guide

These reports are preserved verbatim in the site archive. The guide above is an editorial synthesis and may narrow, qualify, or reorganize claims from the source material.