用双反馈树搜索优化大模型工具规划，提升多步任务效率与准确性。
ToolTree: Efficient LLM Agent Tool Planning via Dual-Feedback Monte Carlo Tree Search and Bidirectional Pruning
- 基于双阶段评估与双向剪枝的树搜索机制，动态规划工具使用顺序。
- 在4个基准上平均性能提升约10%，优于当前最优方案。
- 适合需要复杂工具调度的智能体系统，如自动化决策与跨领域任务处理。
大型语言模型（LLM）代理正被广泛应用于需要与多种外部工具交互的复杂多步任务中。然而，现有工具规划方法多依赖于缺乏远见的贪心策略，难以考虑工具间的依赖关系。本文提出ToolTree，一种受蒙特卡洛树搜索启发的新型规划范式。ToolTree通过双阶段LLM评估与双向剪枝机制，探索可能的工具使用路径，使代理能在执行前和执行后及时修剪低潜力分支，从而做出更明智、自适应的长期决策。在4个基准上的实证评估表明，ToolTree在开放集与封闭集工具规划任务中均显著提升性能，平均优于当前最先进方法约10%，同时保持最高效率。
原文摘要 · Abstract (English)
Large Language Model (LLM) agents are increasingly applied to complex, multi-step tasks that require interaction with diverse external tools across various domains. However, current LLM agent tool planning methods typically rely on greedy, reactive tool selection strategies that lack foresight and fail to account for inter-tool dependencies. In this paper, we present ToolTree, a novel Monte Carlo tree search-inspired planning paradigm for tool planning. ToolTree explores possible tool usage trajectories using a dual-stage LLM evaluation and bidirectional pruning mechanism that enables the agent to make informed, adaptive decisions over extended tool-use sequences while pruning less promising branches before and after the tool execution. Empirical evaluations across both open-set and closed-set tool planning tasks on 4 benchmarks demonstrate that ToolTree consistently improves performance while keeping the highest efficiency, achieving an average gain of around 10\% compared to the state-of-the-art planning paradigm.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。