> ## Documentation Index
> Fetch the complete documentation index at: https://icrl.dev/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# ICRL Algorithm

> How ICRL bootstraps agent performance with self-generated trajectories

## Core Loop

ICRL improves an agent by turning successful episodes into reusable context.

High-level cycle:

1. Attempt task in environment.
2. Store successful trajectory.
3. Retrieve similar prior steps on next tasks.
4. Reuse those examples in prompts.
5. Update utility feedback and curate low-value trajectories.

## Training vs Inference

* `train(...)`: successful runs can be stored (optionally gated by verification).
* `run(...)`: database is read-only for that episode.

## Retrieval Granularity

Both implementations use step-level retrieval in the ReAct loop:

* Plan retrieval: `retrieve_for_plan(goal)`
* Step retrieval: `retrieve_for_step(goal, plan, observation)`

That keeps examples relevant to the exact observation, not only the goal text.

## Curation Signals

Utility is not only “did retrieval lead to success.”

Python also tracks deferred validation metadata (for code-change persistence and supersession), then combines signals into utility scoring.

## Why This Works

* Relevant examples reduce planning errors.
* Step-level examples improve local decisions.
* Curation limits drift from stale or low-signal trajectories.
* Over time, average trajectory quality improves without hand-written few-shot sets.