arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2603.00631cs.AI
收藏

LiTS:一个用于LLM树搜索的模块化框架

LiTS: A Modular Framework for LLM Tree Search

RMIT University(皇家墨尔本理工大学)

Xinzhe Li, Yaguang Tao

AI总结:

本文提出LiTS,一个模块化框架,用于通过树搜索进行LLM推理,展示了其在语言推理、环境规划和工具使用任务中的可组合性,并发现无限动作空间中LLM策略多样性是有效树搜索的瓶颈。

摘要:

LiTS是一个模块化的Python框架,用于通过树搜索进行LLM推理。它将树搜索分解为三个可重用的组件(策略、转移和奖励模型),这些组件可以插入到MCTS和BFS等算法中。基于装饰器的注册机制使领域专家能够通过注册组件扩展到新领域,使算法研究人员能够实现自定义的搜索算法。我们在MATH500(语言推理)、Crosswords(环境规划)和MapEval(工具使用)上展示了可组合性,证明了组件和算法的正交性:组件可以在每个任务类型内跨算法重用,而算法可以在所有组件和领域中工作。我们还报告了一个模式崩溃发现:在无限动作空间中,LLM策略多样性(而不是奖励质量)是有效树搜索的瓶颈。演示视频可在https://youtu.be/nRGX43YrR3I获取。该包在Apache 2.0许可证下发布于https://github.com/xinzhel/lits-llm,包含安装说明和可运行示例,使用户能够重现演示的工作流。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑