No official torrent yet — requesting it tells the flock what to host next. You cannot seed a catalog-only page.
Cataloged from tencent/TCAndon-Router
All models by tencent →
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:
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).
Please refer to GitHub for code usage.
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.
If you use TCAndonRouter in your work, please cite our paper:
from transformers import AutoModelForCausalLM, AutoTokenizerfrom prompt import router_promptfrom utils import load_config
tokenizer = AutoTokenizer.from_pretrained("tencent/TCAndon-Router")model = AutoModelForCausalLM.from_pretrained("tencent/TCAndon-Router", device_map="auto")
agents = load_config('config/hwu64_config.xml')query = "Can you recommend any pub in mg road"prompt = router_prompt.format(agents=agents) + 'user:' + query
messages = [{"role": "user", "content": prompt}]encoding = tokenizer.apply_chat_template( messages, tokenize=True, add_generation_prompt=False, return_tensors="pt")
outputs = model.generate(encoding.to(model.device), max_new_tokens=2048)output_text = tokenizer.decode(outputs[0])python generate_agent_desc.py --dataset hwu64 --limit 50@article{zhao2026TCAndonRouter, title={TCAndonRouter: Adaptive Reasoning Router for Multi-Agent Collaboration}, author={Jiuzhou Zhao, Chunrong Chen, Chenqi Qiao, Lebin Zheng, Minqi Han, Yanchi Liu, Yongzhou Xu, Xiaochuan Xu, Min Zhang}, journal={arXiv preprint:2601.04544}, year={2026}}