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:    TypeError
Message:      Couldn't cast array of type
struct<properties: string, required: list<item: string>, title: string, type: string>
to
{'properties': Json(decode=True), 'required': List(Value('string'))}
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 2315, in cast_table_to_schema
                  cast_array_to_feature(
                  ~~~~~~~~~~~~~~~~~~~~~^
                      table[name] if name in table_column_names else pa.array([None] * len(table), type=schema.field(name).type),
                      ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
                      feature,
                      ^^^^^^^^
                  )
                  ^
                File "/usr/local/lib/python3.14/site-packages/datasets/table.py", line 1861, in wrapper
                  return pa.chunked_array([func(chunk, *args, **kwargs) for chunk in array.chunks])
                                           ~~~~^^^^^^^^^^^^^^^^^^^^^^^^
                File "/usr/local/lib/python3.14/site-packages/datasets/table.py", line 2121, in cast_array_to_feature
                  casted_array_values = _c(array.values, feature.feature)
                File "/usr/local/lib/python3.14/site-packages/datasets/table.py", line 1863, in wrapper
                  return func(array, *args, **kwargs)
                File "/usr/local/lib/python3.14/site-packages/datasets/table.py", line 2071, in cast_array_to_feature
                  _c(children[name] if name in array_fields else null_array, subfeature)
                  ~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
                File "/usr/local/lib/python3.14/site-packages/datasets/table.py", line 1863, in wrapper
                  return func(array, *args, **kwargs)
                File "/usr/local/lib/python3.14/site-packages/datasets/table.py", line 2071, in cast_array_to_feature
                  _c(children[name] if name in array_fields else null_array, subfeature)
                  ~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
                File "/usr/local/lib/python3.14/site-packages/datasets/table.py", line 1863, in wrapper
                  return func(array, *args, **kwargs)
                File "/usr/local/lib/python3.14/site-packages/datasets/table.py", line 2161, in cast_array_to_feature
                  raise TypeError(f"Couldn't cast array of type\n{_short_str(array.type)}\nto\n{_short_str(feature)}")
              TypeError: Couldn't cast array of type
              struct<properties: string, required: list<item: string>, title: string, type: string>
              to
              {'properties': Json(decode=True), 'required': List(Value('string'))}
              
              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.

uuid
string
messages
list
license
string
used_in
list
tools
list
reasoning
string
ff6ab2b0-7551-468c-8606-a7c3b0c75b68
[ { "role": "system", "content": "You are a customer service agent that helps the user. The policy that determines how you should respond to requests from users is described below between the <policy> and </policy> tags.\n\nIn each turn you can either:\n- Send a message to the user.\n- Make a tool call.\nYou...
cc-by-4.0
[ "nano_v3" ]
[ { "type": "function", "function": { "name": "place_order", "description": "Create a new food delivery order", "parameters": { "properties": { "user_id": { "type": "string" }, "restaurants": { "items": { "properties...
on
091a4c59-2ffa-4a65-b243-696155c57684
[ { "role": "system", "content": "You are a customer service agent that helps the user. The policy that determines how you should respond to requests from users is described below between the <policy> and </policy> tags.\n\nIn each turn you can either:\n- Send a message to the user.\n- Make a tool call.\nYou...
cc-by-4.0
[ "nano_v3" ]
[ { "type": "function", "function": { "name": "place_order", "description": "Create a new food delivery order", "parameters": { "properties": { "user_id": { "type": "string" }, "restaurants": { "items": { "properties...
on
596943ce-b426-4f33-bdd1-4cce7185fe46
[ { "role": "system", "content": "You are a customer service agent that helps the user. The policy that determines how you should respond to requests from users is described below between the <policy> and </policy> tags.\n\nIn each turn you can either:\n- Send a message to the user.\n- Make a tool call.\nYou...
cc-by-4.0
[ "nano_v3" ]
[ { "type": "function", "function": { "name": "place_order", "description": "Create a new food delivery order", "parameters": { "properties": { "user_id": { "type": "string" }, "restaurants": { "items": { "properties...
on
78450da8-49f2-4389-8253-4c5597831a44
[ { "role": "system", "content": "You are a customer service agent that helps the user. The policy that determines how you should respond to requests from users is described below between the <policy> and </policy> tags.\n\nIn each turn you can either:\n- Send a message to the user.\n- Make a tool call.\nYou...
cc-by-4.0
[ "nano_v3" ]
[ { "type": "function", "function": { "name": "place_order", "description": "Create a new food delivery order", "parameters": { "properties": { "user_id": { "type": "string" }, "restaurants": { "items": { "properties...
on
d3c4bb85-f770-434d-9030-3471c8bf2952
[ { "role": "system", "content": "You are a customer service agent that helps the user. The policy that determines how you should respond to requests from users is described below between the <policy> and </policy> tags.\n\nIn each turn you can either:\n- Send a message to the user.\n- Make a tool call.\nYou...
cc-by-4.0
[ "nano_v3" ]
[ { "type": "function", "function": { "name": "place_order", "description": "Create a new food delivery order", "parameters": { "properties": { "user_id": { "type": "string" }, "restaurants": { "items": { "properties...
on
ef5270f5-59d9-48f0-81ab-5edbd00361e1
[ { "role": "system", "content": "You are a customer service agent that helps the user. The policy that determines how you should respond to requests from users is described below between the <policy> and </policy> tags.\n\nIn each turn you can either:\n- Send a message to the user.\n- Make a tool call.\nYou...
cc-by-4.0
[ "nano_v3" ]
[ { "type": "function", "function": { "name": "place_order", "description": "Create a new food delivery order", "parameters": { "properties": { "user_id": { "type": "string" }, "restaurants": { "items": { "properties...
on
095a2824-d94e-462c-bd95-8232dafff8dc
[ { "role": "system", "content": "You are a customer service agent that helps the user. The policy that determines how you should respond to requests from users is described below between the <policy> and </policy> tags.\n\nIn each turn you can either:\n- Send a message to the user.\n- Make a tool call.\nYou...
cc-by-4.0
[ "nano_v3" ]
[ { "type": "function", "function": { "name": "place_order", "description": "Create a new food delivery order", "parameters": { "properties": { "user_id": { "type": "string" }, "restaurants": { "items": { "properties...
on
1b366314-e8a6-467e-ba5b-530397e48098
[ { "role": "system", "content": "You are a customer service agent that helps the user. The policy that determines how you should respond to requests from users is described below between the <policy> and </policy> tags.\n\nIn each turn you can either:\n- Send a message to the user.\n- Make a tool call.\nYou...
cc-by-4.0
[ "nano_v3" ]
[ { "type": "function", "function": { "name": "place_order", "description": "Create a new food delivery order", "parameters": { "properties": { "user_id": { "type": "string" }, "restaurants": { "items": { "properties...
on
dff85203-2002-4554-bdcc-c64ab5ef0625
[ { "role": "system", "content": "You are a customer service agent that helps the user. The policy that determines how you should respond to requests from users is described below between the <policy> and </policy> tags.\n\nIn each turn you can either:\n- Send a message to the user.\n- Make a tool call.\nYou...
cc-by-4.0
[ "nano_v3" ]
[ { "type": "function", "function": { "name": "place_order", "description": "Create a new food delivery order", "parameters": { "properties": { "user_id": { "type": "string" }, "restaurants": { "items": { "properties...
on
11a83a93-cbf8-47a1-a3a3-ca0f2ba03100
[ { "role": "system", "content": "You are a customer service agent that helps the user. The policy that determines how you should respond to requests from users is described below between the <policy> and </policy> tags.\n\nIn each turn you can either:\n- Send a message to the user.\n- Make a tool call.\nYou...
cc-by-4.0
[ "nano_v3" ]
[ { "type": "function", "function": { "name": "place_order", "description": "Create a new food delivery order", "parameters": { "properties": { "user_id": { "type": "string" }, "restaurants": { "items": { "properties...
on
d9f64e12-3014-4498-bbdf-ce46acded24b
[ { "role": "system", "content": "You are a customer service agent that helps the user. The policy that determines how you should respond to requests from users is described below between the <policy> and </policy> tags.\n\nIn each turn you can either:\n- Send a message to the user.\n- Make a tool call.\nYou...
cc-by-4.0
[ "nano_v3" ]
[ { "type": "function", "function": { "name": "place_order", "description": "Create a new food delivery order", "parameters": { "properties": { "user_id": { "type": "string" }, "restaurants": { "items": { "properties...
on
ec8fb103-1316-4ec9-878f-3ca56b88156e
[ { "role": "system", "content": "You are a customer service agent that helps the user. The policy that determines how you should respond to requests from users is described below between the <policy> and </policy> tags.\n\nIn each turn you can either:\n- Send a message to the user.\n- Make a tool call.\nYou...
cc-by-4.0
[ "nano_v3" ]
[ { "type": "function", "function": { "name": "place_order", "description": "Create a new food delivery order", "parameters": { "properties": { "user_id": { "type": "string" }, "restaurants": { "items": { "properties...
on
5b4e7933-d21f-46b3-9e0a-10ac0205c85b
[ { "role": "system", "content": "You are a customer service agent that helps the user. The policy that determines how you should respond to requests from users is described below between the <policy> and </policy> tags.\n\nIn each turn you can either:\n- Send a message to the user.\n- Make a tool call.\nYou...
cc-by-4.0
[ "nano_v3" ]
[ { "type": "function", "function": { "name": "place_order", "description": "Create a new food delivery order", "parameters": { "properties": { "user_id": { "type": "string" }, "restaurants": { "items": { "properties...
on
f68ea540-6552-49b1-b5ee-0527bf849e00
[ { "role": "system", "content": "You are a customer service agent that helps the user. The policy that determines how you should respond to requests from users is described below between the <policy> and </policy> tags.\n\nIn each turn you can either:\n- Send a message to the user.\n- Make a tool call.\nYou...
cc-by-4.0
[ "nano_v3" ]
[ { "type": "function", "function": { "name": "place_order", "description": "Create a new food delivery order", "parameters": { "properties": { "user_id": { "type": "string" }, "restaurants": { "items": { "properties...
on
End of preview.

nvidia/Nemotron-Agentic-v1(複製)

データの内容

対話的にツールを使うエージェントを学習させるための、合成の複数ターンの軌跡のデータ。1 行は 1 件の軌跡で、ユーザー、エージェント、ツール環境のやり取りの全体を記録する。対話型エージェントとツール呼び出しの 2 つのサブセットがあり、Qwen3-235B-A22B-Thinking-2507 などの LLM で 3 役を模擬し、別の LLM を審判として一貫しない軌跡を除いたとカードにある。ツール呼び出しのユーザー役には Nemotron-Personas-USA のペルソナを与えた。

データの概要

項目 値
行数・列数 不明(データセットビューアで読めない形式。ファイルの内訳だけを示す)
容量 5.79 GB(ファイル 4 本)
ファイルの形式 jsonl 2
言語 en
公開 public

全データセットの一覧は HYUKI5/dataset-catalog にある。

複製について

nvidia/Nemotron-Agentic-v1 をリビジョン 650d590978ca35c8f1ecea2faf136e5fac421b62 の時点でそのまま複製したもの。中身は変えていない。判断モデル Laya(convaiinnovations/laya)の微調整に使う候補として、調査メモ(Laya 学習用データセット調査)に載せたデータを集めている。

出典

論文

  • 元のカードに論文へのリンクは見つからなかった

アノテーションの方法

データセットの作成日:

作成日: Dec 3, 2025
最終更新日: Dec 3, 2025

微調整に使うときの注意

  • 調査メモの台帳での区分: A(許諾型のライセンスだけで、疑義の注記が無い)。区分は記載の文言で機械的に付けたもので、法的な判定ではない。学習に入れる前に元のカードとライセンスの原文で確かめる。
  • Laya の入力は 2,048 token まで(ModernBERT-large / mmBERT)。長い本文は先頭から黙って切られるので、切れる行は事前に除くか、要約・切り出しをしてから入れる。
  • 分割は記事・文書単位で行い、同じ本文から作った別の問いを学習側と較正側に分けない。温度と閾値は学習に使っていない分割で別々に当てる。

調査メモの記述

メモ 節 ライセンス(記載) 確認 注記
nvidia_nemotron.md 付録. 取得した nvidia 組織のデータセット全件の簡易一覧 (L247) cc-by-4.0 確認済 確認印なし(各ファイルの凡例により確認済扱い) / 原文注記: △ 指示追従・ツール・RL ブレンド。判断ラベル無し(Cascade-RL-RLHF は prompt 列のみ)

元のカード(日本語訳)

以下は元のデータセットのカードの本文を日本語に訳したもの(機械翻訳)。訳に疑問があるときは、末尾の原文を確かめる。


データセットの説明:

Nemotron-Agentic-Tool-Use-v1 データセットは、対話的にツールを使うエージェントとしてのモデルの能力を強化するように設計されている。言語モデルがユーザーの目標を分解し、いつツールを呼び出すかを決め、ツールの出力に基づいて推論して、タスクを確実かつ安全に完了させる、複数ターンの会話に焦点を当てている。

本データセットは商用利用できる。

Nemotron-Agentic-Tool-Use-v1 データセットには、次のサブセットが含まれる:

対話型エージェント

このサブセットは、会話でのツール利用のための、合成された複数ターンの軌跡からなる。大規模言語モデルを使って 3 つの役割をシミュレートして作成した。3 つの役割とは、達成すべきタスクを与えられたユーザー、そのタスクの完了を支援するよう指示されたエージェント、エージェントのツール呼び出しに応答するツール実行環境である。各軌跡は、これらの主体の間のやり取り全体を記録している。

軌跡の品質を確保し、すべての行動が各主体の目標に沿うようにするため、別の言語モデルを審判として使い、データを採点・フィルタリングした。いずれかのステップが一貫性を欠く、筋が通らない、または誤ったツールを使っていると見なされた軌跡は除外した。合成されたやり取りの生成と、この審査の支援の両方に、Qwen3-235B-A22B-Thinking-2507、Qwen3-32B、GPT-OSS-120B、Qwen3-235B-A22B-Instruct-2507 を使った。その結果、信頼でき、目標に沿った会話でのツール利用を重視するデータセットになった。

ツール呼び出し

汎用のツール呼び出しサブセットは、対話型エージェントのサブセットと同様の方法で生成した。公開されているデータセットからツールの集合を集め、ツール利用を含む会話をシミュレートした。このサブセットでは、会話のシミュレーションとターン単位の審査に Qwen3-235B-A22B-Thinking-2507 と Qwen3-235B-A22B-Instruct-2507 を使った。ユーザーのシミュレーターとなる LLM には、nvidia/Nemotron-Personas-USA のユーザーペルソナを与えた。

データセットの所有者:

NVIDIA Corporation

データセットの作成日:

作成日: Dec 3, 2025
最終更新日: Dec 3, 2025

ライセンス・利用規約:

本データセットは Creative Commons Attribution 4.0 International License (CC BY 4.0) の下で提供される。
追加情報: Glaiveai/Glaive-Function-Calling-v2 に対する Apache 2.0 License。

想定される用途:

本データセットは、エージェント型のワークフローと会話でのツール利用のためのモデルを開発・学習する LLM エンジニアと研究チームを対象とする。教師あり微調整、データ拡張、そして、計画を立て、ツールを呼び出し、多段階のやり取りを推論しながら、ユーザーと環境で利用可能なツールに沿った状態を保つ必要があるモデルの評価に適している。軌跡は、エンドツーエンドでツールを使うアシスタントの学習、ツール利用のプランナーやコントローラーの構築とベンチマーク、複数の役割からなるエージェント構成の頑健性の研究に使える。

データセットの特徴づけ

データ収集の方法
ハイブリッド: 人手、合成、自動

ラベル付けの方法
ハイブリッド: 人手、合成、自動

データセットの形式

モダリティ: テキスト
形式: JSONL
構造: テキスト + メタデータ

データセットの定量

Subset Samples
interactive_agent 19,028
tool_calling 316,094
合計 335,122

合計ディスクサイズ: 約 5.5GB

倫理的な配慮:

NVIDIA は、信頼できる AI は共有の責任であると考え、幅広い AI 用途の開発を可能にするための方針と慣行を定めている。利用規約に従ってダウンロードまたは利用される場合、開発者は社内の開発チームと協力し、本データセットが関連する業界と用途の要件を満たすこと、予期しない製品の誤用に対処することを確認すべきである。
品質、リスク、セキュリティ上の脆弱性、または NVIDIA の AI に関する懸念はこちらから報告すること。

原文(英語)

Dataset Description:

The Nemotron-Agentic-Tool-Use-v1 dataset is designed to strengthen models’ capabilities as interactive, tool-using agents. It focuses on multi-turn conversations where language models decompose user goals, decide when to call tools, and reason over tool outputs to complete tasks reliably and safely.

This dataset is ready for commercial use.

The Nemotron-Agentic-Tool-Use-v1 dataset contains the following subsets:

Interactive Agent

This dataset consists of synthetic multi-turn trajectories for conversational tool use, created by simulating three roles with large language models: a user given a task to accomplish, an agent instructed to help complete that task, and a tool execution environment that responds to the agent’s tool calls. Each trajectory captures the full interaction between these entities.

To ensure that the trajectories are high quality and that every action is consistent with each actor’s goals, we employ a separate language model as a judge to score and filter the data, removing trajectories where any step appears inconsistent, incoherent, or that use the incorrect tools. We use Qwen3-235B-A22B-Thinking-2507, Qwen3-32B, GPT-OSS-120B, and Qwen3-235B-A22B-Instruct-2507 both to generate the synthetic interactions and to support this judging process, resulting in a dataset that emphasizes reliable, goal-aligned conversational tool use.

Tool calling

The general-purpose tool-calling subset is generated using a similar method as the Interactive Agent subset. We collect tool sets from publicly available datasets and simulate conversations involving tool use. This subset uses Qwen3-235B-A22B-Thinking-2507 and Qwen3-235B-A22B-Instruct-2507 for simulating the conversation as well as turn-level judgements. The user simulator LLM is seeded with a user persona from nvidia/Nemotron-Personas-USA.

Dataset Owner(s):

NVIDIA Corporation

Dataset Creation Date:

Created on: Dec 3, 2025
Last Modified on: Dec 3, 2025

License/Terms of Use:

This dataset is governed by the Creative Commons Attribution 4.0 International License (CC BY 4.0).
Additional Information: Apache 2.0 License for Glaiveai/Glaive-Function-Calling-v2.

Intended Usage:

This dataset is intended for LLM engineers and research teams developing and training models for agentic workflows and conversational tool use. It is suitable for supervised fine-tuning, data augmentation, and evaluation of models that must plan, call tools, and reason over multi-step interactions while staying aligned with the user and available tools in an environment. The trajectories can be used to train end-to-end tool-using assistants, build and benchmark tool-use planners or controllers, and study robustness of multi-role agent setups.

Dataset Characterization

Data Collection Method
Hybrid: Human, Synthetic, Automated

Labeling Method
Hybrid: Human, Synthetic, Automated

Dataset Format

Modality: Text
Format: JSONL
Structure: Text + Metadata

Dataset Quantification

Subset Samples
interactive_agent 19,028
tool_calling 316,094
Total 335,122

Total Disk Size: ~ 5.5GB

Ethical Considerations:

NVIDIA believes Trustworthy AI is a shared responsibility and we have established policies and practices to enable development for a wide array of AI applications.  When downloaded or used in accordance with our terms of service, developers should work with their internal developer teams to ensure this dataset meets requirements for the relevant industry and use case and addresses unforeseen product misuse.
Please report quality, risk, security vulnerabilities or NVIDIA AI Concerns here

Downloads last month
60