Qwen-0.8B-AgentJSON

AIREV Qwen-0.8B-AgentJSON

World's first sub-1B parameter model with functional tool calling capability.

Built by AIREV for the OnDemand Agentic AI Platform.

Key Results

What This Model Does

Generates structured JSON execution plans for tool/plugin orchestration. Given a user request and available tools, it produces a valid JSON object specifying which tools to call, with what parameters, and in what order.

Evaluation Results

Production Plugin Eval (Real OnDemand Plugins, 50 samples)

By Query Complexity

Training Pipeline

This model was trained using a novel multi-stage approach developed by AIREV:

Stage 1: Supervised Fine-Tuning (SFT)

• Base model: Qwen 3.5-0.8B
• 47K+ curated samples with reasoning traces and structured JSON outputs
• Real production plugin schemas from the OnDemand platform (2,176 plugins)
• LLM-evaluated data quality filtering (score >= 8/10)
• Full fine-tune (not LoRA) — research shows full FT outperforms at sub-1B scale

Stage 2: Progressive Curriculum GRPO

• Group Relative Policy Optimization with a novel 4-phase progressive reward curriculum
• The reward progressively increases in difficulty across training:
  • Phase 1: JSON structural validity
  • Phase 2: Required field presence
  • Phase 3: Correct tool selection (prompt-grounded)
  • Phase 4: Parameter quality and completeness
• Innovation: Noise injection for zero-variance groups prevents common GRPO failure modes
• Prompt-aware reward function verifies selected tools against available options in the input

Why This Matters

1. Sub-1B tool calling is novel — no published model under 3B demonstrates functional tool calling
2. Progressive Curriculum GRPO — a new approach enabling skill stacking in small models
3. Edge deployment viable — 400MB quantized, 30 tok/s on Snapdragon 8 Elite, <3s response time

Model Specs

Intended Use

• Primary: On-device agentic AI for tool orchestration on edge devices (AR glasses, mobile, IoT)
• Platform: Built for the OnDemand Agentic AI Platform (3,000+ tools)
• Best for: 1-2 step tool calling queries
• Not recommended for: Complex multi-step workflows (5+ tools)

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model = AutoModelForCausalLM.from_pretrained("airev-ae/Qwen-0.8B-AgentJSON", torch_dtype=torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained("airev-ae/Qwen-0.8B-AgentJSON")

messages = [
    {"role": "system", "content": "You are an AI agent orchestrator. Generate a JSON execution plan."},
    {"role": "user", "content": "Search for the latest AI news"}
]

text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tokenizer(text, return_tensors="pt").to(model.device)

output = model.generate(**inputs, max_new_tokens=512, temperature=0.8, do_sample=True)
print(tokenizer.decode(output[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True))

Limitations

• Best accuracy on 1-2 tool queries; degrades on 3+ tool orchestration
• Trained on OnDemand plugin schema format
• Recommended: use with JSON validation at inference for production
• Temperature 0.7-0.8 produces best results

Citation

@misc{airev2026agentjson,
  title={AIREV Qwen-0.8B-AgentJSON: Sub-1B Tool Calling via Progressive Curriculum GRPO},
  author={AIREV FZ-LLC},
  year={2026},
  url={https://huggingface.co/airev-ae/Qwen-0.8B-AgentJSON}
}

---

Built by AIREV | OnDemand Platform | Abu Dhabi, UAE

Trained with Progressive Curriculum GRPO — a novel approach for sub-1B structured output generation.