HomeResearch LibraryLATS: Language Agent Tree Search
system architectureChapter 2ICML 2024 · 2023

LATS: Language Agent Tree Search

Andy Zhou (UIUC), Kai Yan (UIUC)

Abstract

We present LATS, a general framework for language agent search that combines Monte Carlo Tree Search with LLM-based agents. LATS uses LLM-generated heuristics to guide tree search over agent trajectories.

Eigenvector Insight — Zone III / PASF-PADE AnalysisNot part of the original paper
Eigenvector Research — Marco van Hurne
How this paper contributes to solving the Zone III problem (PASF-PADE)

LATS bridges classical AI search with modern LLM agents. For Zone III planning, the ability to search over possible trajectories before committing to execution is a significant reliability improvement.

Why AI is not sufficient for Zone III without this

Zone III refers to high-complexity, high-risk, long-running agentic workflows — the class of enterprise AI deployments where a single failure can cascade across hundreds of steps. Standard AI models, trained to predict the next token, are not inherently designed for durable, governed, multi-step execution. This paper addresses one or more of the structural gaps that make Zone III deployments unsafe without explicit architectural intervention.

Key Contributions

  • →MCTS for language agents
  • →LLM-guided search heuristics
  • →Trajectory-level planning

Topics

tree searchMCTSagent planningsearch algorithms