Skip to main content
Task is the unit of work in rLLM: one problem instance — a single math row, a single sandboxed coding task — described as pure data. The Runner is the orchestrator that drives an AgentFlow on a Task, resolves the verifier from the Task itself, and writes rewards back. There is one code path for both data benchmarks (gsm8k-style) and sandbox benchmarks (Harbor-style).

​
The Task data model

from dataclasses import dataclass, field
from pathlib import Path
from typing import Any

@dataclass
class Task:
    id: str                                          # Stable identifier
    instruction: str | list[dict]                    # What the agent sees
    metadata: dict[str, Any] = field(default_factory=dict)
    dataset_dir: Path = field(default_factory=Path)  # Directory holding dataset.toml
    sub_dir: Path | None = None                      # Per-task subdir (sandbox tasks)

    @property
    def task_dir(self) -> Path:
        """For sandbox tasks: dataset_dir / sub_dir. Otherwise: dataset_dir."""
        return self.dataset_dir / self.sub_dir if self.sub_dir else self.dataset_dir
Task is intentionally minimal. It says what the problem is and where its files live. It does not carry an evaluator reference, a sandbox handle, or a rendered prompt template — those are produced lazily by the Runner from on-disk config.

​
Instruction

instruction is what the agent sees in the user message. Three sources, in priority order:
  1. instruction.md.tpl — a template in the dataset directory rendered with the row, supporting {{field}} placeholders. List-valued fields (e.g. MCQ choices) become a lettered block: (A) ...\n(B) ....
  2. instruction_field — a column name declared in dataset.toml.
  3. instruction.md — a literal file (one per task directory; sandbox shape).
For VLM benchmarks (category = "vlm" in dataset.toml), the loader produces a list of OpenAI-style content blocks instead of a string, with images encoded as inline data URIs.

​
Metadata

metadata is the side channel between the dataset and the verifier:
  • Data tasks: the source row (or the subset of fields named in metadata_fields). This is where ground truth, MCQ choices, expected answer, etc. live.
  • Sandbox tasks: the parsed task.toml, plus convenience keys lifted from common sections (workdir, agent_user, verifier_user, verifier_timeout, setup_commands, …).
A reward function reads task.metadata["ground_truth"]. A sandbox verifier uses task.task_dir to find its files.

​
Two physical shapes

A “benchmark” on disk is one of two shapes — both produce list[Task]:

​
1. Rows-with-shared-verifier (gsm8k-style)

my-math-bench/
├── dataset.toml                   # Declares verifier + instruction template
├── data/
│   └── test.jsonl                 # One row per problem
└── instruction.md.tpl             # Optional template
Each row in data/<split>.jsonl becomes one Task. dataset_dir is the benchmark directory; sub_dir is None. The verifier is shared across all rows.

​
2. Task-per-directory (Harbor-style sandbox)

my-swe-bench/
├── dataset.toml
├── task-001/
│   ├── task.toml                  # Per-task config + verifier
│   ├── instruction.md             # Per-task prompt
│   ├── environment/               # Dockerfile, setup scripts
│   └── tests/                     # Verifier scripts
├── task-002/
│   └── ...
Each subdirectory becomes one Task. sub_dir is set, so task.task_dir resolves to the per-task directory and the verifier finds its files there. The Runner detects whether a sandbox is needed and provisions one.

​
Loading a benchmark

BenchmarkLoader autodetects the shape: 
from rllm.tasks import BenchmarkLoader

result = BenchmarkLoader.load("./my-math-bench")
result.tasks            # list[Task]
result.harness_name     # Suggested AgentFlow (CLI overridable with --agent)
result.sandbox_backend  # "docker" | "local" | "modal" | None
Three shapes are recognised:
  1. dataset.toml + data/<split>.jsonl → simple/data dataset.
  2. dataset.toml + subdirectories with task.toml (or listed under [[tasks]]) → sandbox dataset.
  3. Single task.toml at the root, or autodiscovered subdirectories with task.toml → still produces Tasks.
Catalog datasets (gsm8k, MATH-500, MMLU, …) materialise on first use into ~/.rllm/datasets/<name>/, then load through the same path.

​
The Runner

rllm.runner.Runner runs a single Task end-to-end: 
from rllm.runner import Runner

runner = Runner(
    agent_flow=my_agent_flow,
    sandbox_backend="docker",        # Optional override
    evaluator_override=None,         # Optional CLI-side override
)
episode = await runner.run(task, agent_config)
The pipeline:
1

Read verifier config

Resolve the task’s verifier from task.toml (per-task) or dataset.toml (shared). The [verifier] section names either an import_path (Python module) or a name (legacy reward-fn registry key).
2

Provision sandbox if needed

If the task or AgentFlow requires a sandbox, build one from task.task_dir/environment/ (Dockerfile, image, setup commands). Sandbox backends: docker, local, modal.
3

Run the AgentFlow

Call agent_flow.run(task, config) (or arun if defined) to produce an Episode with one or more Trajectories.
4

Resolve and run the Evaluator

Build an evaluator from the verifier config: a Python evaluate function for data tasks, or a shell-script runner for sandbox tasks. Pass it (task, episode) to get an EvalOutput.
5

Write rewards back

Set episode.is_correct from the EvalOutput, and write EvalOutput.reward onto each trajectory so trajectories are ready for RL training.

​
Running many tasks

run_dataset is the parallel front-end on top of Runner — it’s what rllm eval uses internally: 
from rllm.eval import run_dataset
from rllm.tasks import BenchmarkLoader

result = BenchmarkLoader.load("./my-math-bench")

eval_result, episodes = await run_dataset(
    tasks=result.tasks,
    agent_flow=my_agent,
    base_url="http://localhost:4000",
    model="gpt-4o-mini",
    concurrency=64,
    sandbox_backend=result.sandbox_backend,
)
print(eval_result.score, eval_result.signals)
Concurrency is bounded by min(concurrency, agent_flow.max_concurrent). Sandboxed flows get a fresh per-task agent_flow copy so sandbox state doesn’t leak.

​
Why this split

Before this refactor, eval and training each had their own task abstraction, and sandbox tasks went through a different pipeline than data tasks. That split made it hard to share verifiers, mix shapes in one benchmark suite, or move a benchmark from “in-memory rows” to “on-disk task directories” without rewriting glue. The new model — pure-data Task + a single Runner that reads verifier config off disk — means:
  • Data tasks and sandbox tasks share the same Episode-producing pipeline.
  • Verifiers travel with the dataset (in dataset.toml / task.toml), not in agent code.
  • The CLI, training loop, and SDK all consume the same Task and Runner, so behaviour stays consistent across entry points.