haive.agents.reasoning_and_critique.self_discover.adapter.agent¶

Self-Discover Adapter Agent implementation.

Classes¶

AdapterAgent

Agent that adapts selected reasoning modules for specific tasks.

Module Contents¶

class haive.agents.reasoning_and_critique.self_discover.adapter.agent.AdapterAgent(name='adapter', engine=None, **kwargs)¶

Bases: haive.agents.simple.SimpleAgent

Agent that adapts selected reasoning modules for specific tasks.

The Adapter Agent is the second stage in the Self-Discover workflow. It takes the reasoning modules selected by the Selector Agent and adapts them to be concrete and actionable for the specific task at hand.

name¶

Agent identifier (default: “adapter”)

engine¶

LLM configuration for the agent

Example

>>> from haive.core.engine.aug_llm import AugLLMConfig
>>>
>>> config = AugLLMConfig(temperature=0.4)
>>> adapter = AdapterAgent(engine=config)
>>>
>>> result = await adapter.arun({
...     "selected_modules": "1. Critical thinking: Analyze assumptions...",
...     "task_description": "Design a recommendation system"
... })

Initialize the Adapter 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