SMART - Sequential Multi-Agent Reasoning Technique (0.5.0+)

SMART is a sequential multi-agent reasoning technique.

v1.1
smart_core.py
Python · 804 lines
187    class Valves(BaseModel):188        OPENAI_BASE_URL: str = Field(189            default="https://openrouter.ai/api/v1",190            description="Base URL for OpenAI API endpoints",191        )192        OPENAI_API_KEY: str = Field(default="", description="Primary API key")193        MODEL_PREFIX: str = Field(default="SMART", description="Prefix before model ID")194        SMALL_MODEL: str = Field(195            default="openai/gpt-4o-mini", 196            description="Model for small tasks",197        )198        LARGE_MODEL: str = Field(

The SMART (Sequential Multi-Agent Reasoning Technique) system is a powerful pipeline for enhanced language model capabilities. It includes:

  • Planning Agent: Prepares incoming user requests for subsequent agents in the chain.
  • Reasoning Agent: Handles internal thought processes, planning, and thinking.
  • Tool-use Agent: Interfaces with various tools to gather information or perform actions.
  • User-interaction Agent: Manages direct communication with the user.

Key features:

  • Adaptive model selection based on task complexity
  • Multi-step reasoning process
  • Integration with external tools
  • Customizable prompts for each agent in the chain
  • Advanced Planning and internal thought

SMART enhances the problem-solving capabilities of language models by breaking down complex tasks into manageable steps and leveraging specialized agents for different aspects of the process.

0
0

The SMART (Sequential Multi-Agent Reasoning Technique) system is a powerful pipeline for enhanced language model capabilities. It includes:

  • Planning Agent: Prepares incoming user requests for subsequent agents in the chain.
  • Reasoning Agent: Handles internal thought processes, planning, and thinking.
  • Tool-use Agent: Interfaces with various tools to gather information or perform actions.
  • User-interaction Agent: Manages direct communication with the user.

Key features:

  • Adaptive model selection based on task complexity
  • Multi-step reasoning process
  • Integration with external tools
  • Customizable prompts for each agent in the chain
  • Advanced Planning and internal thought

SMART enhances the problem-solving capabilities of language models by breaking down complex tasks into manageable steps and leveraging specialized agents for different aspects of the process.

0
0