MigrationBench

This cookbook trains a Java 8→17 code-migration agent on MigrationBench. Unlike the other cookbooks, the agent does not run in-process as an AgentFlow plugin — it runs inside an AWS Bedrock AgentCore Runtime container built and deployed from the agentcore-rl-toolkit repo. rLLM drives rollouts over the network and trains the policy locally with the verl backend. Because the agent lives in an external container, there is no pip install -e cookbooks/<name> plugin and no rllm eval/train CLI entry point. The cookbook in cookbooks/migrationbench/ only handles the rLLM side: registering the dataset from S3 metadata and launching verl training against the remote runtime.

Pattern

Aspect	Value
Loop shape	Multi-turn coding agent, running inside an AgentCore Runtime container
Dataset	`migration_bench` — MigrationBench Java repos, registered from S3 metadata
Runtime	AWS Bedrock AgentCore Runtime (remote, auto-scaling microVMs)
Backend	verl only (distributed multi-GPU)
Reward shape	Agent runs `mvn` build/tests in-container, writes the reward to S3; rLLM polls it
Model (reference)	Qwen3-Coder-30B-A3B-Instruct (LoRA), tested on a single 8×B200 node with verl 0.8.0

Prerequisites

The agent code, container build, and dataset upload all live in the toolkit. Build and deploy the agent by following the strands_migration_agent example. That produces the three inputs this cookbook needs:

An AgentCore agent runtime ARN — the deployed container that performs the migrations.
A data S3 bucket — holds the prepared MigrationBench repo tarballs and their metadata.json, written by the toolkit’s preprocess.py. The container downloads repos from here at runtime, and prepare_migrationbench_data.py reads its metadata to register the dataset.
An output S3 bucket — where the agent writes rollout results (rewards, etc.); rLLM polls it each rollout. May differ from the data bucket.

Install rLLM with the verl and agentcore extras

# rLLM + verl backend (vLLM) + AgentCore runtime client
uv pip install -e ".[verl,agentcore]"

# Megatron deps for the verl training backend
bash scripts/install_megatron.sh <cu128|cu129|...>

Deploy the agent and upload data (agentcore-rl-toolkit)

git clone https://github.com/awslabs/agentcore-rl-toolkit
cd agentcore-rl-toolkit/examples/strands_migration_agent

# Upload prepared MigrationBench repos + metadata to your data bucket
python preprocess.py --s3-bucket-name <data-bucket>

# Build + deploy the agent container (see the example README) → records the agent runtime ARN

Configure the environment

Run the remaining steps from the cookbook folder (cd cookbooks/migrationbench); the train script sources .env from the current directory. Copy the example and fill it in:

cp .env.example .env
# edit .env:
#   AGENTCORE_AGENT_ARN=arn:aws:bedrock-agentcore:<region>:<account>:runtime/<name>
#   AGENTCORE_S3_BUCKET=<output-bucket>

python prepare_migrationbench_data.py --s3-bucket-name <data-bucket>

This downloads only the small metadata.json files from s3://<data-bucket>/tars/{train,test}/, then registers migration_bench/{train,test} with the rLLM DatasetRegistry:

Train — repos under tars/train/ with num_test_cases > 0.
Test — all repos under tars/test/.

Run training

bash train_agentcore_migrationbench_verl.sh

The script sources .env for the agent ARN and output bucket, then runs verl with rllm.remote_runtime.backend=agentcore so rollouts execute in the deployed container. Tune MODEL_PATH, parallelism (TP/EP/CP), batch sizes, and trainer.n_gpus_per_node/nnodes in the script to match your hardware.

See the AWS Bedrock AgentCore page for how the remote runtime, the model gateway, and S3 fit together during training.

​Pattern

​Prerequisites

Pattern

Prerequisites