RecursiveMAS/Mixture-Math-DeepSeek-R1-Distill-Qwen-1.5B
The RecursiveMAS/Mixture-Math-DeepSeek-R1-Distill-Qwen-1.5B is a 1.5 billion parameter model developed by RecursiveMAS, specifically designed as a Math Specialist Agent within the RecursiveMAS multi-agent framework. Based on DeepSeek-R1-Distill-Qwen-1.5B, this model excels at mathematical reasoning tasks by collaborating with other specialized agents through iterative latent state exchange. It operates within a 32768 token context length and is intended for integration into multi-agent systems rather than standalone plain-text generation.
Loading preview...
Overview
RecursiveMAS/Mixture-Math-DeepSeek-R1-Distill-Qwen-1.5B is a 1.5 billion parameter model developed by RecursiveMAS, functioning as a Math Specialist Agent within the RecursiveMAS multi-agent framework. This framework, detailed in the paper "Recursive Multi-Agent Systems" (arXiv:2604.25917), enables scalable agent collaboration through latent-space recursion. The model is built upon the DeepSeek-R1-Distill-Qwen-1.5B base and is specifically optimized for mathematical reasoning.
Key Characteristics
- Role-Specific Agent: This model is not a general-purpose language model but a specialized component designed to perform mathematical reasoning within a larger multi-agent system.
- Mixture-Style Collaboration: It operates within a "Mixture-Style" collaboration setting, where it exchanges and refines latent states with other domain-specialized agents to generate final responses.
- RecursiveMAS Framework: It is an integral part of the RecursiveMAS framework, which treats multi-agent systems as unified recursive computations, enhancing collaboration efficiency.
- Context Length: Supports a substantial context length of 32768 tokens.
Intended Use
This model is specifically designed for integration into the RecursiveMAS multi-agent framework to handle mathematical reasoning tasks. It is not intended for standalone plain-text generation and requires the full RecursiveMAS system for proper functionality. Developers should refer to the project's GitHub repository for detailed usage instructions and to understand its role within the broader multi-agent architecture.