> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.nvidia.com/nemo/relay/llms.txt.
> For full documentation content, see https://docs.nvidia.com/nemo/relay/llms-full.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.nvidia.com/nemo/relay/_mcp/server.

# Trait Learner

> Background learner that updates adaptive state from observed runs.

Generated from `cargo doc --no-deps -p nemo-relay -p nemo-relay-adaptive -p nemo-relay-ffi`.

<pre />

Background learner that updates adaptive state from observed runs.

## Required Methods

#### `process_run`

<pre />

Process one observed run and update backend state plus the hot cache.

##### Parameters

* `run`: Telemetry record to learn from.
* `backend`: Storage backend used to persist learner state.
* `hot_cache`: Shared in-memory cache to refresh with the latest results.

##### Returns

A future that resolves when the learner has finished processing the run.

## Implementors

### `impl Learner for AcgLearner`

<pre />

### `impl Learner for ToolParallelismLearner`

<pre />

### `impl Learner for LatencySensitivityLearner`

<pre />