Agent Loops

Agent Loops

Enable LLMs to reason, plan, and take autonomous actions.

When to Use

• Multi-step problem solving
• Tasks requiring planning
• Autonomous tool use
• Self-correcting workflows

ReAct Pattern (Reasoning + Acting)

REACT_PROMPT = """You are an agent that reasons step by step.

For each step, respond with:
Thought: [your reasoning about what to do next]
Action: [tool_name(arg1, arg2)]
Observation: [you'll see the result here]

When you have the final answer:
Thought: I now have enough information
Final Answer: [your response]

Available tools: {tools}

Question: {question}
"""

async def react_loop(question: str, tools: dict, max_steps: int = 10) -> str:
    """Execute ReAct reasoning loop."""
    history = REACT_PROMPT.format(tools=list(tools.keys()), question=question)

    for step in range(max_steps):
        response = await llm.chat([{"role": "user", "content": history}])
        history += response.content

        # Check for final answer
        if "Final Answer:" in response.content: