base_model:
- meta-llama/Llama-3.2-3B-Instruct
license: mit
pipeline_tag: text-generation
library_name: transformers
Sequential-Scaled-Critic-Llama3.2-3B
🌐 Project Page | 💻 Code | 📄 Paper
RecursiveMAS is a multi-agent framework that scales agent collaboration through latent-space recursion. It 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, this Critic Agent is responsible for reviewing and refining the initial plan produced by the Planner Agent, which is then passed to the Solver Agent for final solution generation.
Model Details
| Item | Description |
|---|---|
| Model | Sequential-Scaled-Critic-Llama3.2-3B |
| Collaboration Style | Sequential-Scaled |
| Agent Role | Critic Agent |
| Base Model | Llama-3.2-3B-Instruct |
⚠️ 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 entire multi-agent system as follows:
from system_loader import load_mas_system
# Load the whole MAS pipeline
mas = load_mas_system(
style="sequential_scaled",
device="cuda",
trust_remote_code=True,
)
planner = mas.agents["planner"].model
critic = mas.agents["critic"].model
solver = mas.agents["solver"].model
For detailed setup and inference instructions, please refer to the GitHub repository.
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},
}