Hugging Face's logo

Datasets:
saulpzh
/
Meta-Task-Data

Tasks:
Text Generation
Languages:
English
ArXiv:
Tags:
terminal-agents
code-agent
task-synthesis
agent-trajectories
sft
License:
Dataset card Data Studio Files
xet
 Community
Dataset Preview
Duplicate
The full dataset viewer is not available (click to read why). Only showing a preview of the rows.
The dataset generation failed
Error code:   DatasetGenerationError
Exception:    CastError
Message:      Couldn't cast
messages: list<item: struct<role: string, content: string>>
  child 0, item: struct<role: string, content: string>
      child 0, role: string
      child 1, content: string
special_ability: string
data_type: string
source: string
id: string
synthetic_model: string
tag: struct<code_agent: string>
  child 0, code_agent: string
reward: double
to
{'messages': List({'role': Value('string'), 'content': Value('string')}), 'special_ability': Value('string'), 'data_type': Value('string'), 'source': Value('string'), 'id': Value('string'), 'synthetic_model': Value('string'), 'tag': {'code_agent': Value('string')}}
because column names don't match
Traceback:    Traceback (most recent call last):
                File "/usr/local/lib/python3.14/site-packages/datasets/builder.py", line 1835, in _prepare_split_single
                  for key, table in generator:
                                    ^^^^^^^^^
                File "/src/services/worker/src/worker/job_runners/config/parquet_and_info.py", line 621, in wrapped
                  for item in generator(*args, **kwargs):
                              ~~~~~~~~~^^^^^^^^^^^^^^^^^
                File "/usr/local/lib/python3.14/site-packages/datasets/packaged_modules/json/json.py", line 361, in _generate_tables
                  self._cast_table(pa_table, json_field_paths=json_field_paths),
                  ~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
                File "/usr/local/lib/python3.14/site-packages/datasets/packaged_modules/json/json.py", line 132, in _cast_table
                  pa_table = table_cast(pa_table, self.info.features.arrow_schema)
                File "/usr/local/lib/python3.14/site-packages/datasets/table.py", line 2381, in table_cast
                  return cast_table_to_schema(table, schema)
                File "/usr/local/lib/python3.14/site-packages/datasets/table.py", line 2309, in cast_table_to_schema
                  raise CastError(
                  ...<3 lines>...
                  )
              datasets.table.CastError: Couldn't cast
              messages: list<item: struct<role: string, content: string>>
                child 0, item: struct<role: string, content: string>
                    child 0, role: string
                    child 1, content: string
              special_ability: string
              data_type: string
              source: string
              id: string
              synthetic_model: string
              tag: struct<code_agent: string>
                child 0, code_agent: string
              reward: double
              to
              {'messages': List({'role': Value('string'), 'content': Value('string')}), 'special_ability': Value('string'), 'data_type': Value('string'), 'source': Value('string'), 'id': Value('string'), 'synthetic_model': Value('string'), 'tag': {'code_agent': Value('string')}}
              because column names don't match
              
              The above exception was the direct cause of the following exception:
              
              Traceback (most recent call last):
                File "/src/services/worker/src/worker/job_runners/config/parquet_and_info.py", line 1379, in compute_config_parquet_and_info_response
                  parquet_operations, partial, estimated_dataset_info = stream_convert_to_parquet(
                                                                        ~~~~~~~~~~~~~~~~~~~~~~~~~^
                      builder, max_dataset_size_bytes=max_dataset_size_bytes
                      ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
                  )
                  ^
                File "/src/services/worker/src/worker/job_runners/config/parquet_and_info.py", line 956, in stream_convert_to_parquet
                  builder._prepare_split(split_generator=splits_generators[split], file_format="parquet")
                  ~~~~~~~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
                File "/usr/local/lib/python3.14/site-packages/datasets/builder.py", line 1702, in _prepare_split
                  for job_id, done, content in self._prepare_split_single(
                                               ~~~~~~~~~~~~~~~~~~~~~~~~~~^
                      gen_kwargs=gen_kwargs, job_id=job_id, **_prepare_split_args
                      ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
                  ):
                  ^
                File "/usr/local/lib/python3.14/site-packages/datasets/builder.py", line 1887, in _prepare_split_single
                  raise DatasetGenerationError("An error occurred while generating the dataset") from e
              datasets.exceptions.DatasetGenerationError: An error occurred while generating the dataset

Need help to make the dataset viewer work? Make sure to review how to configure the dataset viewer, and open a discussion for direct support.

messages
list
special_ability
string
data_type
string
source
string
id
string
synthetic_model
string
tag
dict
[{"role":"user","content":"You are an AI assistant tasked with solving command-line tasks in a Linux(...TRUNCATED)
code_agent
sft
terminalbench
meta-task-0008__p9ar4jt
openai/Qwen3.5-397B-A17B-FP8
{ "code_agent": "terminus-2" }
[{"role":"user","content":"You are an AI assistant tasked with solving command-line tasks in a Linux(...TRUNCATED)
code_agent
sft
terminalbench
meta-task-0009__ug65fe5
openai/Qwen3.5-397B-A17B-FP8
{ "code_agent": "terminus-2" }
[{"role":"user","content":"You are an AI assistant tasked with solving command-line tasks in a Linux(...TRUNCATED)
code_agent
sft
terminalbench
meta-task-0043__gnfqgsw
openai/Qwen3.5-397B-A17B-FP8
{ "code_agent": "terminus-2" }
[{"role":"user","content":"You are an AI assistant tasked with solving command-line tasks in a Linux(...TRUNCATED)
code_agent
sft
terminalbench
meta-task-0046__qmpbhhj
openai/Qwen3.5-397B-A17B-FP8
{ "code_agent": "terminus-2" }
[{"role":"user","content":"You are an AI assistant tasked with solving command-line tasks in a Linux(...TRUNCATED)
code_agent
sft
terminalbench
meta-task-0061__8ksbvyt
openai/Qwen3.5-397B-A17B-FP8
{ "code_agent": "terminus-2" }
[{"role":"user","content":"You are an AI assistant tasked with solving command-line tasks in a Linux(...TRUNCATED)
code_agent
sft
terminalbench
meta-task-0085__trjynfc
openai/Qwen3.5-397B-A17B-FP8
{ "code_agent": "terminus-2" }
[{"role":"user","content":"You are an AI assistant tasked with solving command-line tasks in a Linux(...TRUNCATED)
code_agent
sft
terminalbench
meta-task-0089__kgvfpnr
openai/Qwen3.5-397B-A17B-FP8
{ "code_agent": "terminus-2" }
[{"role":"user","content":"You are an AI assistant tasked with solving command-line tasks in a Linux(...TRUNCATED)
code_agent
sft
terminalbench
meta-task-0106__3grpabc
openai/Qwen3.5-397B-A17B-FP8
{ "code_agent": "terminus-2" }
[{"role":"user","content":"You are an AI assistant tasked with solving command-line tasks in a Linux(...TRUNCATED)
code_agent
sft
terminalbench
meta-task-0118__i6qqgtg
openai/Qwen3.5-397B-A17B-FP8
{ "code_agent": "terminus-2" }
[{"role":"user","content":"You are an AI assistant tasked with solving command-line tasks in a Linux(...TRUNCATED)
code_agent
sft
terminalbench
meta-task-0122__dfracvj
openai/Qwen3.5-397B-A17B-FP8
{ "code_agent": "terminus-2" }
End of preview.

Meta-Task-Data

Data produced by Meta-Task, the official implementation of "Meta-Task: Turning Terminal Task Synthesis into a Terminal Task for Scalable Agent Training" (arXiv:2607.27929).

Meta-Task redefines terminal task synthesis as a Terminal-Bench-format terminal task: an agent runs inside a Docker container to generate, execute, and verify new terminal tasks.

Contents

Path Contents
tasks/meta_tasks_v1.tar.gz 3,220 synthesized terminal tasks. Each is a complete Terminal-Bench package (instruction.md, task.toml, environment/, solution/, tests/). Extracts to v1/<task-name>/.
trajectories/sft_trajectories_3221.jsonl 3,221 SFT trajectories, one JSON object per line.

Trajectory format

Each line of sft_trajectories_3221.jsonl:

Field Description
messages Conversation turns (role, content) of the agent solving the task.
id Name of the source task (matches a directory under v1/).
data_type sft
special_ability code_agent
source terminalbench
synthetic_model Model that generated the trajectory (Qwen3.5-397B-A17B-FP8).
tag e.g. {"code_agent": "terminus-2"} — the agent scaffold used.

Loading 

import json, tarfile

with tarfile.open("tasks/meta_tasks_v1.tar.gz") as tf:
    tf.extractall("tasks/")          # -> tasks/v1/<task-name>/

with open("trajectories/sft_trajectories_3221.jsonl") as f:
    trajectories = [json.loads(line) for line in f]

Links

License

Apache-2.0.
Downloads last month
83
Total file size:
903 MB

Paper for saulpzh/Meta-Task-Data