agents.reasoning_and_critique.self_discover.structurer.agent¶

Self-Discover Structurer Agent implementation.

Classes¶

StructurerAgent

Agent that creates structured reasoning plans from adapted modules.

Module Contents¶

class agents.reasoning_and_critique.self_discover.structurer.agent.StructurerAgent(name='structurer', engine=None, **kwargs)¶

Bases: haive.agents.simple.SimpleAgent

Agent that creates structured reasoning plans from adapted modules.

The Structurer Agent is the third stage in the Self-Discover workflow. It takes the adapted reasoning modules and organizes them into a coherent, step-by-step plan for solving the specific task.

name¶: Agent identifier (default: “structurer”)

engine¶: LLM configuration for the agent

Example

>>> from haive.core.engine.aug_llm import AugLLMConfig
>>>
>>> config = AugLLMConfig(temperature=0.2)
>>> structurer = StructurerAgent(engine=config)
>>>
>>> result = await structurer.arun({
...     "adapted_modules": "1. Critical analysis: Look for biases...",
...     "task_description": "Design a recommendation system"
... })

Initialize the Structurer Agent.

Parameters:

name (str) – Name for the agent
engine (haive.core.engine.aug_llm.AugLLMConfig) – LLM configuration (if not provided, creates default)
**kwargs – Additional arguments passed to SimpleAgent