base_model:
- Qwen/Qwen3.5-4B
license: mit
pipeline_tag: text-generation
library_name: transformers
Sequential-Scaled-Solver-Qwen3.5-4B
🌐 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 Sequential-Scaled setting, the Solver Agent is responsible for producing the final response based on the planning and critique information refined through RecursiveLink modules.
Model Details
| Item | Description |
|---|---|
| Model | Sequential-Scaled-Solver-Qwen3.5-4B |
| Collaboration Style | Sequential-Scaled |
| Agent Role | Solver 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.
Usage
To use this model within the RecursiveMAS framework, you can load the system using the provided system loader from the official repository:
from system_loader import load_mas_system
# Load the full multi-agent system for the Sequential-Scaled style
mas = load_mas_system(
style="sequential_scaled",
device="cuda",
trust_remote_code=True,
)
# Access the individual agent models
planner = mas.agents["planner"].model
critic = mas.agents["critic"].model
solver = mas.agents["solver"].model
Model Collections for RecursiveMAS
| Style | Model Collection |
|---|---|
| Sequential-Style | 🤗 HuggingFace |
| Mixture-Style | 🤗 HuggingFace |
| Distillation-Style | 🤗 HuggingFace |
| Deliberation-Style | 🤗 HuggingFace |
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},
}