haive.agents.reasoning_and_critique.lats.agent
==============================================

.. py:module:: haive.agents.reasoning_and_critique.lats.agent

.. autoapi-nested-parse::

   Language Agent Tree Search (LATS) agent.

   Composes ReactAgent (candidate generation with tools) and SimpleAgent
   (reflection/scoring with structured output) in a Monte Carlo Tree Search loop.

   Graph: START -> generate -> [expand <-> should_continue] -> finish -> END

   The generator and reflector are real haive agents (ReactAgent, SimpleAgent)
   that use our tested infrastructure for LLM calls, tool use, and structured output.



Classes
-------

.. autoapisummary::

   haive.agents.reasoning_and_critique.lats.agent.LATSAgent


Functions
---------

.. autoapisummary::

   haive.agents.reasoning_and_critique.lats.agent.create_lats_agent


Module Contents
---------------

.. py:class:: LATSAgent

   Bases: :py:obj:`haive.agents.base.agent.Agent`


   Look-Ahead Tree Search using ReactAgent + SimpleAgent composition.

   - Generator: ReactAgent with tools for candidate creation
   - Reflector: SimpleAgent with structured output (Reflection model)
   - Tree logic: UCB1 selection, backpropagation, depth limiting


   .. py:method:: build_graph()

      Build LATS graph using haive.core BaseGraph.



   .. py:method:: compile(**kwargs)

      Compile: build agents lazily, use BaseGraph.to_langgraph(), no checkpointer.



   .. py:method:: get_best_answer(result)

      Extract best answer string from result.



   .. py:method:: run(input_data, **kwargs)

      Run LATS. Accepts string or dict with 'input' key.



.. py:function:: create_lats_agent(tools=None, model='gpt-4o-mini', **kwargs)

   Factory for LATS agent.