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

# Continuous Retraining

> Feed collected traces back into training, round by round

Every round of the loop adds a new version of the training data. The deployed model then improves round by round, while each round stays comparable with earlier rounds in the same experiment.

## Traces Into Datasets

Reviewed traces go into a new version of a [dataset](https://docs.trymonte.ai/datasets/overview.md). A corrected reply is a demonstration row for [SFT](https://docs.trymonte.ai/training/sft.md), and a reviewer's edit with the model's original reply is a pair for [DPO](https://docs.trymonte.ai/training/dpo.md). Add the earlier rows and the new ones together, and the dataset gets a new version, such as `support-replies@2`. Each run records the exact version it trained on.

## Traces Into Environments

A trace's request becomes a task row in the [training environment](https://docs.trymonte.ai/environments/tasks.md). The task takes the trace's messages and tools in the task format. For a conversation over several requests, join its traces by a session ID in `metadata`. The reviewer fills in the grader fields, such as `should_escalate` and `expected_category`. Adding the task file again makes a new version, such as `support-escalation-train@2`, for a [GRPO](https://docs.trymonte.ai/training/grpo.md) run:

```bash theme={null}
monte env add --training support_escalation --as support-escalation-train
```

## Each Round

Train from the deployed checkpoint with `--parent`, on the new versions. Pick the checkpoint on the development eval, and compare it task by task with the deployed checkpoint. Score the held-out eval once for each round. Its change from the baseline compares directly with every earlier round, but a held-out eval scored over many rounds starts to overstate gains, so refresh it with new traffic in a new experiment every few rounds. Then move traffic in steps, and the deployment keeps collecting traces for the next round. Every step is a CLI command, so a team can run a round from a script on its own schedule.

## New Kinds of Requests

When traffic shifts, pinned evals no longer cover it. Add the new requests to an eval environment as a new version, and create a new experiment with it. Take its baselines before the next run.

Each `monte dataset add` and `monte env add --training` checks the new rows against every eval, so a trace that matches an eval task does not leak into training unnoticed.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.