Choose a learning method

Choose the editable adapter content first, then a method that understands it. A template defines the files, exports, and checks; an Evolver defines how evidence becomes an update. Sharing the interface does not make all template–method combinations meaningful.

Goal	Starting method	Template	Additional inputs
Improve a short instruction document with few moving parts	Prompt-only	prompt-only@1.0	Codex CLI, Linux learner environment
Let a coding agent edit several files, skills, or code	Codex / Claude	A template with the intended learnable paths	Authenticated learner CLI
Search text candidates with validation-based selection	GEPA	Start with prompt-only	Validation split and GEPA extra
Make bounded skill edits with a validation gate	SkillOpt	Start with prompt-only or the paper seed	Validation split and SkillOpt extra
Refine a harness per task from trajectories without labels, with a library of adopted harnesses	Harness²	harness2-codex@1.0	Learner model endpoint, Codex, the harness2 extra
Refine a policy, sub-agents, skills and memory in place from each step’s trajectories, without a gate	Continual Harness	continual-harness@1.0	Learner model endpoint, Codex
Build a persistent world model from an ordered environment stream	MWM	mwm	Evidence store, deployment description, tools, Linux learner environment
Learn the framework contract offline	Quick Start	Prompt-only with a teaching learner	Included toy tasks

Compare the work behind each step

All methods share the main acting batch. The table describes additional work, excluding retries and any task-specific service overhead. Call counts vary with evidence, candidates, and settings.

Method	Additional model / acting work	Persistent learner state	Final selection
Prompt-only	One Codex learner session per step that rewrites ADAPTER.md; no candidate rollout gate	Notes the session keeps in state/	Current adapter
Codex / Claude	A multi-action learner session; candidate tests depend on what the learner does	Saved files and optional supported session handle	Current adapter unless the method customizes finalization
GEPA	Initial-parent validation, reflection, child minibatch tests, and validation for a child that passes the minibatch criterion	Candidate pool, validation scores, per-candidate next file	Highest retained validation mean
SkillOpt	Reflection/merge/ranking calls, validation (cached by skill content), optional epoch-end and final validation work	Current/best skills, validation cache, update history and meta skill	Retained best, with optional final promotion
Harness²	Two editors, a composer and a reflector per task, plus three probe executions (k = 1); the adapter stays H0	Library of adopted harnesses with lessons	Unchanged adapter; the stream’s own deliverables are the result
Continual Harness	Four Refiner calls per step (policy, sub-agents, skills, memory); no candidate rollout, no validation	Step log in state/; the memory the agent writes comes back with each trajectory	Current adapter
MWM	Maintenance and a learner session per eligible block, plus native bootstrap/retry behavior	World-model adapter plus method/session records	Current world-model adapter

use_gate: false in SkillOpt removes the ordinary improvement requirement, not the validation calls. GEPA’s minibatch criterion is separate from its validation-based parent/final selection. Use run records to compare actual calls and costs rather than treating every step as equal work.

Decide what the learner may change

For context-only experiments, start with ADAPTER.md. To learn skills or tool implementations, declare those paths as learnable in a custom template. Changing evolver.name does not expand those permissions. The customization tutorial shows how to create a separate template identity.

A text optimizer writes selected text files. A coding-agent Evolver can make more general edits, within the template’s rules. MWM has its own memory, programs, evidence protocol, and learner contract; choosing it requires a task integration that supplies those resources.

Plan the data and comparison

• Keep test tasks for evaluation. GEPA and SkillOpt additionally require validation tasks for candidate selection.

• For an ordered stream, set data.shuffle: false; choose batch boundaries according to the environment’s timeline.

• Hold acting model, tools, judge, and evaluation protocol fixed when comparing methods.

• Compare against both no adapter and the starting adapter. Their difference measures the template’s initial contribution.

• Record learning calls, candidate evaluations, and acting calls. Equal training steps do not imply equal cost.

The framework checks declared needs and file validity. It does not automatically establish learning effectiveness or choose a method for you. Continue with Train an experiment.