--- base_model: - Qwen/Qwen3.5-4B license: mit --- # Deliberation-Toolcaller-Qwen3.5-4B [๐ Project Page](https://recursivemas.github.io) | [๐ป Code](https://github.com/RecursiveMAS/RecursiveMAS) | [๐ Paper](https://arxiv.org/abs/2604.25917) 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. ## Model Details | Item | Description | |---|---| | Model | Deliberation-Toolcaller-Qwen3.5-4B | | Collaboration Style | Deliberation-Style | | Agent Role | Tool-Caller Agent | | Base Model | Qwen3.5-4B | โ ๏ธ **Note:** This checkpoint is a **role-specific agent** in [**RecursiveMAS**](https://arxiv.org/abs/2604.25917), rather than a standalone model intended for plain-text generation. For detailed usage instructions, please refer to our [GitHub repository](https://github.com/RecursiveMAS/RecursiveMAS). ## Model Collections for RecursiveMAS | Style | Model Collection | |---|---| | Sequential-Style | [๐ค HuggingFace](https://huggingface.co/collections/RecursiveMAS/sequential-style-recursivemas) | | Mixture-Style | [๐ค HuggingFace](https://huggingface.co/collections/RecursiveMAS/mixture-style-recursivemas) | | Distillation-Style | [๐ค HuggingFace](https://huggingface.co/collections/RecursiveMAS/distillation-style-recursivemas) | | Deliberation-Style | [๐ค HuggingFace](https://huggingface.co/collections/RecursiveMAS/deliberation-style-recursivemas) | ## Experiment Results