Nex-N1: Agentic Models Trained via a Unified Ecosystem for Large-Scale Environment Construction
Paper • 2512.04987 • Published • 85
Datasets:
messages list | tools list | uuid string | generator string |
|---|---|---|---|
[
{
"role": "system",
"content": "You are OpenHands agent, a helpful AI assistant that can interact with a computer to solve tasks.\n\n<ROLE>\nYour primary role is to assist users by executing commands, modifying code, and solving technical problems effectively. You should be thorough, methodical, and priorit... | [
{
"type": "function",
"function": {
"name": "execute_bash",
"description": "Execute a bash command in the terminal within a persistent shell session.\n\n\n### Command Execution\n* One command at a time: You can only execute one bash command at a time. If you need to run multiple commands sequent... | 164629d8-21c5-4b1a-802a-111d47b1fd5d | DeepSeek-V3.1-Nex-N1 |
[{"role":"system","content":"You are OpenHands agent, a helpful AI assistant that can interact with (...TRUNCATED) | [{"type":"function","function":{"name":"execute_bash","description":"Execute a bash command in the t(...TRUNCATED) | c17b2171-514e-4f9a-bcad-9db6a6a639b3 | DeepSeek-V3.1-Nex-N1 |
[{"role":"system","content":"You are OpenHands agent, a helpful AI assistant that can interact with (...TRUNCATED) | [{"type":"function","function":{"name":"execute_bash","description":"Execute a bash command in the t(...TRUNCATED) | bcece353-354b-4c45-a7c5-b5166ab8cc4e | DeepSeek-V3.1-Nex-N1 |
[{"role":"system","content":"You are OpenHands agent, a helpful AI assistant that can interact with (...TRUNCATED) | [{"type":"function","function":{"name":"execute_bash","description":"Execute a bash command in the t(...TRUNCATED) | 31b0bc2e-a8e3-4095-9317-063db6fb3133 | DeepSeek-V3.1-Nex-N1 |
[{"role":"system","content":"You are OpenHands agent, a helpful AI assistant that can interact with (...TRUNCATED) | [{"type":"function","function":{"name":"execute_bash","description":"Execute a bash command in the t(...TRUNCATED) | 41fbf1e0-01ec-444c-9d3c-2f39b830953a | DeepSeek-V3.1-Nex-N1 |
[{"role":"system","content":"You are OpenHands agent, a helpful AI assistant that can interact with (...TRUNCATED) | [{"type":"function","function":{"name":"execute_bash","description":"Execute a bash command in the t(...TRUNCATED) | c3deb95f-f2ea-40ef-bf48-6f7ec7a30c42 | DeepSeek-V3.1-Nex-N1 |
[{"role":"system","content":"You are OpenHands agent, a helpful AI assistant that can interact with (...TRUNCATED) | [{"type":"function","function":{"name":"execute_bash","description":"Execute a bash command in the t(...TRUNCATED) | c2a3dbb5-05cd-42c1-a50e-625cccf4356c | DeepSeek-V3.1-Nex-N1 |
[{"role":"system","content":"You are OpenHands agent, a helpful AI assistant that can interact with (...TRUNCATED) | [{"type":"function","function":{"name":"execute_bash","description":"Execute a bash command in the t(...TRUNCATED) | af5df577-b35b-4987-940e-c5c5787b8af5 | DeepSeek-V3.1-Nex-N1 |
[{"role":"system","content":"You are OpenHands agent, a helpful AI assistant that can interact with (...TRUNCATED) | [{"type":"function","function":{"name":"execute_bash","description":"Execute a bash command in the t(...TRUNCATED) | 1b60aa26-ac28-4437-81f6-16dee8e21712 | DeepSeek-V3.1-Nex-N1 |
[{"role":"system","content":"You are OpenHands agent, a helpful AI assistant that can interact with (...TRUNCATED) | [{"type":"function","function":{"name":"execute_bash","description":"Execute a bash command in the t(...TRUNCATED) | f0205751-4019-47f2-b822-e4f7c123c3dd | DeepSeek-V3.1-Nex-N1 |
End of preview. Expand in Data Studio
Nex Agent-SFT Dataset
Paper | Code | Project Page
Dataset Description
This dataset is specifically designed for training the agentic capabilities of Large Language Models (LLMs). The dataset covers multiple agent scenarios and aims to enhance model performance in autonomous decision-making, tool usage, code generation, and interactive task handling. We reselected some of the training queries from the NEX-N1 training dataset and regenerated the responses based on DeepSeek-V3.1-Nex-N1. This data can provide a reference for the community to train and develop new agent models.
Dataset Distribtion
| Category | Value |
|---|---|
| agentic_code | 24796 |
| agent | 11749 |
| chat | 2079 |
| html | 8332 |
| tool_call | 9737 |
| Total | 69008 |
Dataset Structure
Each example in the dataset contains the standard instruction-tuning data points as follow:
uuid(str): a unique identifiermessages(list): message format used for supervised fine-tuning (this contains systerm prompt, user prompt, assistant responses and tool response)tools(list): the list of tool definitions, where each definition includes a tool name, a description, and parameters defined by properties.generator(str): the model name for generating responses.
- Downloads last month
- 11