agents.reasoning_and_critique.self_discover.executor.agent¶

Self-Discover Executor Agent implementation.

Classes¶

ExecutorAgent

Agent that executes structured reasoning plans to solve tasks.

Module Contents¶

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

Bases: haive.agents.simple.SimpleAgent

Agent that executes structured reasoning plans to solve tasks.

The Executor Agent is the fourth and final stage in the Self-Discover workflow. It takes the structured reasoning plan and systematically executes it to arrive at a comprehensive solution for the original task.

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

engine¶: LLM configuration for the agent

Example

>>> from haive.core.engine.aug_llm import AugLLMConfig
>>>
>>> config = AugLLMConfig(temperature=0.5)
>>> executor = ExecutorAgent(engine=config)
>>>
>>> result = await executor.arun({
...     "reasoning_structure": "Step 1: Analyze requirements...",
...     "task_description": "Design a recommendation system"
... })

Initialize the Executor 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