---
title: AgenticQwen-8B
canonical_url: "https://www.modelscope.ai/models/PAI/AgenticQwen-8B"
md_url: "https://www.modelscope.ai/models/PAI/AgenticQwen-8B.md"
repository: PAI/AgenticQwen-8B
last_updated: 2026-10-29
license: apache-2.0
pipeline_tag: fill-mask
tasks:
  - fill-mask
model_type:
  - qwen3
architectures:
  - Qwen3ForCausalLM
base_model:
  - Qwen/Qwen3-8B
base_model_relation: finetune
parameters: 8.2B
tensor_type:
  - BF16
library_name:
  - safetensors
  - pytorch
frameworks:
  - Pytorch
downloads: 171
stars: 0
tags:
  - safetensors
  - qwen3
  - agentic
  - tool-use
---

# AgenticQwen-8B

> AgenticQwen-8B - An open-source model by PAI on ModelScope. AgenticQwen-8B is a small agentic language model trained on Qwen3-8B, designed for multi-step reasoning and tool use. It is trained with a multi-round reinforcement learning (GRPO-style) pipeline…

PAI/AgenticQwen-8B is a 8.2B-parameter fill-mask model on ModelScope. licensed under apache-2.0. derived from Qwen/Qwen3-8B.

- **Repository**: PAI/AgenticQwen-8B
- **License**: apache-2.0
- **Tasks**: fill-mask
- **Parameters**: 8.2B
- **Base model**: Qwen/Qwen3-8B
- **Tags**: safetensors, qwen3, agentic, tool-use
- **Downloads**: 171
- **Stars**: 0
- **Last updated**: 2026-10-29

Source: https://www.modelscope.ai/models/PAI/AgenticQwen-8B

---

# Model Description

AgenticQwen-8B is a small agentic language model trained on Qwen3-8B, designed for multi-step reasoning and tool use. It is trained with a multi-round reinforcement learning (GRPO-style) pipeline and a dual "data flywheel" mechanism that continually increases task difficulty for both reasoning and agentic workflows.