Downloads · 30 days
39
3% of all-time downloads
RecursiveMAS/Deliberation-Toolcaller-Qwen3.5-4B
Deliberation-Toolcaller-Qwen3.5-4B is a machine learning model from RecursiveMAS. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as mit.
Downloads · 30 days
39
3% of all-time downloads
All-time downloads
1.1K
Public
Parameters
4.2B
8.5 GB on disk
Likes
4
Public
Click a slice to open those files.
.safetensors8.4 GB · 99%
From the Hugging Face model README
🌐 Project Page | 💻 Code | 📄 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 Deliberation-Style setting, the Tool-Caller Agent performs tool-oriented reasoning and execution, while collaborating with the Reflector Agent through RecursiveLink modules for iterative refinement.
| Item | Description |
|---|---|
| Model | Deliberation-Toolcaller-Qwen3.5-4B |
| Collaboration Style | Deliberation-Style |
| Agent Role | Tool-Caller Agent |
| Base Model | Qwen3.5-4B |
⚠️ 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.
| Style | Model Collection |
|---|---|
| Sequential-Style | 🤗 HuggingFace |
| Mixture-Style | 🤗 HuggingFace |
| Distillation-Style | 🤗 HuggingFace |
| Deliberation-Style | 🤗 HuggingFace |
@inproceedings{
recursivemas2026,
title={Recursive Multi-Agent Systems},
author={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},
booktitle={The Fortieth Annual Conference on Neural Information Processing Systems},
year={2026},
url={https://openreview.net/forum?id=ML0KFwGcPG}
}