mlsanityData to 7 Oct 2026

LiTS: A Modular Framework for LLM Tree Search

arXiv 2603.00631 ↗First posted 28 Feb 2026cs.AIcited by 1

On the map: LLM reasoning → Test-time compute and efficient thinking

Abstract (arXiv)

LiTS is a modular Python framework for LLM reasoning via tree search. It decomposes tree search into three reusable components (Policy, Transition, and RewardModel) that plug into algorithms like MCTS and BFS. A decorator-based registry enables domain experts to extend to new domains by registering components, and algorithmic researchers to implement custom search algorithms. We demonstrate composability on MATH500 (language reasoning), Crosswords (environment planning), and MapEval (tool use), showing that components and algorithms are orthogonal: components are reusable across algorithms within each task type, and algorithms work across all components and domains. We also report a mode-collapse finding: in infinite action spaces, LLM policy diversity (not reward quality) is the bottleneck for effective tree search. A demonstration video is available at https://youtu.be/nRGX43YrR3I. The package is released under the Apache 2.0 license at https://github.com/xinzhel/lits-llm, including installation instructions and runnable examples that enable users to reproduce the demonstrated workflows.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Placed in Test-time compute and efficient thinking, one of 17 directions in LLM reasoning. Builds on 5 of its 11 references that are in the map. First posted on arXiv 28 Feb 2026.

Builds on

5 of 11 references.

Closest ancestors · 1

Same direction, newest first

  1. 2025Chain-in-Tree: Back to Sequential Reasoning in LLM Tree Search30 Sep

Other references · 4

  1. 2023Reasoning with Language Model is Planning with World Modelcited by 846
  2. 2023Language Agent Tree Search Unifies Reasoning Acting and Planning in Language Modelscited by 551
  3. 2024ReST-MCTS*: LLM Self-Training via Process Reward Guided Tree Searchcited by 338
  4. 2025Beyond the Surface: Measuring Self-Preference in LLM Judgmentscited by 30

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026When Does Memory Help Multi-Trajectory Inference for Tool-Use LLM Agents?cited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2024Enhancing LLM Reasoning with Reward-guided Tree Search
  2. 2024LiteSearch: Efficacious Tree Search for LLM
  3. 2025Unifying Tree Search Algorithm and Reward Design for LLM Reasoning: A Survey
  4. 2026LinTree: Improving LLM Reasoning with Explicitly Structured Search Histories
  5. 2025LLM-First Search: Self-Guided Exploration of the Solution Space
  6. 2025MITS: Enhanced Tree Search Reasoning for LLMs via Pointwise Mutual Information
  7. 2025Policy Guided Tree Search for Enhanced LLM Reasoning
  8. 2023Autonomous Tree-search Ability of Large Language Models