Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2603.00631 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914573781565440 |
|---|---|
| author | Li, Xinzhe Tao, Yaguang |
| author_facet | Li, Xinzhe Tao, Yaguang |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_00631 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | LiTS: A Modular Framework for LLM Tree Search Li, Xinzhe Tao, Yaguang Artificial Intelligence 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. |
| title | LiTS: A Modular Framework for LLM Tree Search |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2603.00631 |