Mixture-Summarizer-Qwen3.5-2B

🌐 Project Page | πŸ’» Code | πŸ“„ Paper

We introduce RecursiveMAS, a multi-agent framework that scales agent collaboration through latent-space recursion. RecursiveMAS treats a multi-agent system as a unified recursive computation, where heterogeneous agents iteratively exchange, refine, and evolve their latent states across recursion rounds. In the Mixture-Style setting, the Summarizer Agent integrates outputs from domain-specialized agents and produces the final response through recursive latent-space collaboration.

Model Details

Item Description
Model Mixture-Summarizer-Qwen3.5-2B
Collaboration Style Mixture-Style
Agent Role Summarizer Agent
Base Model Qwen3.5-2B

⚠️ Note: This checkpoint is a role-specific agent in RecursiveMAS, rather than a standalone model intended for plain-text generation.
For detailed usage instructions, please refer to our GitHub repository.

Model Collections for RecursiveMAS

Style Model Collection
Sequential-Style πŸ€— HuggingFace
Mixture-Style πŸ€— HuggingFace
Distillation-Style πŸ€— HuggingFace
Deliberation-Style πŸ€— HuggingFace

Experiment Results

RecursiveMAS Experiment Results

Citation

@misc{recursivemas,
      title={Recursive Multi-Agent Systems}, 
      author={Xiyuan Yang and Jiaru Zou and Rui Pan and Ruizhong Qiu and Pan Lu and Shizhe Diao and Jindong Jiang and Hanghang Tong and Tong Zhang and Markus J. Buehler and Jingrui He and James Zou},
      year={2026},
      eprint={2604.25917},
      archivePrefix={arXiv},
      primaryClass={cs.AI},
      url={https://arxiv.org/abs/2604.25917}, 
}
Downloads last month
61
Safetensors
Model size
2B params
Tensor type
BF16
Β·
Inference Providers NEW
This model isn't deployed by any Inference Provider. πŸ™‹ Ask for provider support

Model tree for RecursiveMAS/Mixture-Summarizer-Qwen3.5-2B

Finetuned
Qwen/Qwen3.5-2B
Finetuned
(130)
this model
Quantizations
2 models

Collection including RecursiveMAS/Mixture-Summarizer-Qwen3.5-2B

Paper for RecursiveMAS/Mixture-Summarizer-Qwen3.5-2B