amityco/amity-sigma-thinking-v3r

Amity Sigma Thinking v3r

A 4-billion parameter model fine-tuned for agentic customer service tasks, achieving 78.51% Pass@1 on the Tau2-Bench retail domain - outperforming models 50-400x its size.

Model Highlights

Performance Comparison

Tau2-Bench Retail Domain Pass@1 scores:

Key Achievements

• —Outperforms GPT-4.1 (1.7T parameters) by 4.5 percentage points
• —Outperforms Qwen3-Max (340-407B parameters) by 3.1 percentage points
• —Only 2.9% behind Claude Opus 4, which is approximately 50x larger

Full Tau2-Bench Results

Usage

vLLM Serving (Recommended)

vllm serve amityco/amity-sigma-thinking-v3r \
    --reasoning-parser deepseek_r1 \
    --enable-auto-tool-choice \
    --tool-call-parser hermes \
    --max-model-len 45000 \
    --trust-remote-code

For multi-GPU setups:

vllm serve amityco/amity-sigma-thinking-v3r \
    --reasoning-parser deepseek_r1 \
    --enable-auto-tool-choice \
    --tool-call-parser hermes \
    --max-model-len 45000 \
    --trust-remote-code \
    --tensor-parallel-size 8

Hardware Requirements

Training Methodology

Qwen3-4B-Thinking (Base)
    ↓
ROAD Optimization (Policy Enhancement)
    ↓
Synthetic Data Generation (Amity Sigma)
    ↓
Human-in-the-Loop Feedback
    ↓
GRPO Fine-tuning
    ↓
Amity Sigma v3r

Training Details

• —Base Model: Qwen3-4B-Thinking
• —Optimization: ROAD (Auto Optimization for Agentic Tasks)
• —Fine-tuning: GRPO on multi-turn interaction data
• —Data: Synthetic customer service conversations with human-in-the-loop feedback

Cost Efficiency

Estimated Cost per 1,000 Customer Interactions

Self-Hosting Benefits

• —Run on modest hardware (single A100 or 2x RTX 4090)
• —Predictable costs without per-token pricing
• —Data privacy - no external API calls
• —Low latency with local inference

Intended Use

This model is designed for:

• —Customer service automation
• —Order management and support
• —Multi-turn conversational agents
• —Tool-calling and function execution

Limitations

• —Optimized primarily for retail domain; airline and telecom performance is lower
• —Requires vLLM with specific configuration for optimal tool-calling
• —Best suited for English language interactions

Links

• —Tau2-Bench Submission: PR #137
• —Implementation: github.com/amity-arac/amity-sigma-tau2-run
• —Tau2-Bench: github.com/sierra-research/tau2-bench

Citation

@misc{amity-sigma-v3r,
  title={Amity Sigma Thinking v3r: Efficient Agentic Model for Customer Service},
  author={Amity},
  year={2026},
  url={https://huggingface.co/amityco/amity-sigma-thinking-v3r}
}

References

• —ROAD: Auto Optimization for Agentic Tasks
• —Tau2-Bench: A Benchmark for Conversational AI Agents
• —Qwen3-4B-Thinking

Contact

For questions or feedback: touchapon@amity.co