GATE让大模型在多任务中自适应演化工具图谱，提速近4倍。
GATE: Graph-based Adaptive Tool Evolution Across Diverse Tasks
- 基于图结构动态构建可复用工具链，支持跨任务演化。
- 在Minecraft中比顶尖方法快4.3倍，代码与代理任务分别提升9.23%和10.03%。
- 适合需要持续优化工具链的智能体与自动化系统开发者。
大型语言模型（LLMs）在工具生成方面展现出巨大潜力，但现有框架往往难以高效构建可靠工具集，且局限于单任务场景。为此，我们提出GATE（基于图的自适应工具跨任务演化框架），一种可在多种情境下动态构建并演化分层可复用工具图谱的自适应框架。我们在开放任务（Minecraft）、基于智能体的任务（TextCraft、DABench）以及代码生成任务（MATH、Date、TabMWP）上评估了GATE。结果表明，GATE在Minecraft中实现里程碑完成速度最高提升4.3倍，相较于现有工具生成方法，在代码生成任务上平均提升9.23%，在代理任务上提升10.03%。GATE展示了自适应演化的强大能力，在工具数量、复杂度与功能之间取得良好平衡，同时保持高效率。代码与数据已开源于\url{https://github.com/ayanami2003/GATE}。
原文摘要 · Abstract (English)
Large Language Models (LLMs) have shown great promise in tool-making, yet existing frameworks often struggle to efficiently construct reliable toolsets and are limited to single-task settings. To address these challenges, we propose GATE (Graph-based Adaptive Tool Evolution), an adaptive framework that dynamically constructs and evolves a hierarchical graph of reusable tools across multiple scenarios. We evaluate GATE on open-ended tasks (Minecraft), agent-based tasks (TextCraft, DABench), and code generation tasks (MATH, Date, TabMWP). Our results show that GATE achieves up to 4.3x faster milestone completion in Minecraft compared to the previous SOTA, and provides an average improvement of 9.23% over existing tool-making methods in code generation tasks and 10.03% in agent tasks. GATE demonstrates the power of adaptive evolution, balancing tool quantity, complexity, and functionality while maintaining high efficiency. Code and data are available at \url{https://github.com/ayanami2003/GATE}.
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。