Create README.md

README.md

@@ -0,0 +1,76 @@
+# TCAndon-Router
+
+<p align="center">
+    <img src="https://raw.githubusercontent.com/Tencent/TCAndon-Router/refs/heads/main/assets/router.png" width="500"/>
+</p>
+
+<p align="center">
+    &nbsp;&nbsp; <a href="https://github.com/Tencent/TCAndon-Router">Github</a>&nbsp;&nbsp; | &nbsp;&nbsp; 📑 <a href="https://arxiv.org/abs/TCAndonRouter">Paper</a> &nbsp;&nbsp;
+</p>
+
+
+## 🌟 Introduction
+
+In multi-agent systems, the ability to select the appropriate agent(s) to handle a user query is a key determinant of overall system performance.
+
+TCAndonRouter is a reasoning-centric multi-intent routing module whose primary role is to perform agent routing in multi-agent systems.
+Beyond agent routing, TCAndonRouter can be applied to any intent-routing scenario, including agent skill selection.
+
+The main advantages of TCAndonRouter include:
+
++ Designed specifically for real-world enterprise applications
++ Supports dynamic onboarding of new agents (intents) New agents can be added simply by appending their descriptions, without retraining
++ Provides transparent and interpretable routing decisions, improving explainability, robustness, and cross-domain generalization, and making post-deployment bad-case analysis easier
++ Effectively resolves agent conflicts caused by overlapping responsibilities, leading to higher-quality final responses. When multiple agents are applicable, TCAndonRouter preserves all relevant agents. Each downstream agent generates its own response, and a Refining Agent subsequently merges these outputs into a single final answer
+
+TCAndonRouter is trained using Supervised Fine-Tuning (SFT) followed by Reinforcement Learning (DAPO), and achieves state-of-the-art performance on large-scale, real-world enterprise datasets, including HWU64, MINDS14, SGD, and the Tencent Cloud ITSM dataset(QCloud).
+
+| **Models**             | **CLINC150** | **HWU64** | **MINDS14** | **SGD**   | **QCloud**      |
+|------------------------|--------------|-----------|-------------|-----------|-----------------|
+| GPT-5.1                | 93.84        | 85.59     | 95.59       | 73.90     | 92.80/93.06     |
+| Claude-Sonnet-4.5      | **94.21**    | 87.40     | 96.20       | 76.02     | 88.82/94.25     |
+| DeepSeek-v3.1-terminus | 88.29        | 88.10     | 95.72       | 79.70     | 94.09/91.89     |
+| ArcRouter              | 62.98        | 69.33     | 91.79       | 65.59     | -               |
+| Qwen3-Embedding-4B     | 57.21        | 54.27     | 94.12       | 37.02     | -               |
+| Qwen3-4B-Instruct-2507 | 70.12        | 80.29     | 90.08       | 58.74     | 82.23/79.44     |
+| **TCAndonRouter**           | 91.25        | **91.63** | **96.70**   | **91.58** | **95.21/92.78** |
+
+## 🔧 How to use
+
+Please refer to [GitHub](https://github.com/Tencent/TCAndon-Router) for code usage.
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+from prompt import router_prompt
+from utils import load_config
+
+tokenizer = AutoTokenizer.from_pretrained("tencent/TCAndon-Router")
+model = AutoModelForCausalLM.from_pretrained("tencent/TCAndon-Router")
+
+agents = load_config('config/hwu64_config.xml')
+query = "Can you recommend any pub in mg road"
+
+prompt = router_prompt.format(agents=agents) + 'user:' + query
+response = model.generate(prompt)
+print(response)
+```
+### Generate Agent Descriptions
+
+If you want to use TCAndonRouter on your own dataset, you need to provide agent descriptions. The required format is defined in `config/xxx_config.xml`.
+You can generate agent descriptions using an LLM via generate_agent_desc.py, or write them manually.
+```shell
+python generate_agent_desc.py --dataset hwu64 --limit 50
+```
+
+## 🤝 Citation
+
+If you use TCAndonRouter in your work, please cite our paper:
+
+```
+@article{zhao2025TCAndonRouter,
+  title={TCAndonRouter: Adaptive Reasoning Router for Multi-Agent Collaboration},
+  author={Jiuzhou Zhao et al.},
+  journal={arXiv},
+  year={2025}
+}
+```