smolagents-lats

LATS (Language Agent Tree Search) agent for smolagents.

Instead of a linear ReAct loop, LATSAgent expands a search tree, scores branches with UCT, and reflects on failed paths.

Based on the paper: arxiv.org/abs/2310.04406

Install

pip install smolagents-lats

Usage

from smolagents import HfApiModel
from smolagents_lats import LATSAgent

model = HfApiModel()

agent = LATSAgent(
    tools=[],
    model=model,
    n_branches=3,
    max_depth=4,
)

result = agent.run("What is the 10th Fibonacci number?")
print(result)

How it works

• Expand — generates n_branches candidate actions at each step
• Score — asks the LLM to score each branch (0.0 → 1.0)
• UCT select — picks the most promising unexplored branch
• Reflect — on failed paths, generates a verbal self-critique fed back as context

Parameters

License

MIT