Large language model (LLM) agents increasingly rely on agent harnesses that manage context, tools, and multi-turn execution, making tools a central interface for acting in realistic digital environments. As harness-connected tool ecosystems expand to hundreds or thousands of APIs, services, and task-specific skills, exhaustive tool schema injection becomes costly and imposes a closed-world assumption that limits agents to a predefined static inventory. Retrieval-augmented tool selection offers a natural alternative, but existing one-shot retrieval methods often fail to align isolated tool descriptions with the agent's true task intention, especially in long-horizon tasks where required capabilities emerge through decomposition, observations, and newly induced subgoals. We propose SING, an intention-aware active tool discovery framework that builds an intention-tool graph linking user intentions, tool capabilities, and tool collaboration patterns, and dynamically retrieves tools according to evolving task states. Using a unified corpus of 7,471 tools, we evaluate SING on three real-world tool-use benchmarks. SING improves Global Recall@5 by up to 59.8% and downstream success rate by up to 28.9% over baselines, while reducing full-corpus tool-schema exposure by 99.8%, demonstrating that intention-aware graph structure enables more accurate and context-efficient tool discovery in large-scale agentic ecosystems.

翻译：大型语言模型（LLM）智能体越来越依赖智能体框架来管理上下文、工具和多轮执行，使工具成为在现实数字环境中行动的核心接口。随着框架连接的工具生态系统扩展到数百或数千个API、服务及任务专用技能，穷举式工具模式注入变得成本高昂，并施加了封闭世界假设，将智能体限制在预定义的静态清单中。增强检索的工具选择提供了自然替代方案，但现有的一次性检索方法常无法将孤立的工具描述与智能体的真实任务意图对齐，特别是在长周期任务中，所需能力通过任务分解、观察和新诱导的子目标逐步显现。我们提出SING，一种意图感知的主动工具发现框架，通过构建连接用户意图、工具能力与工具协作模式的意图-工具图，并根据演化任务状态动态检索工具。利用包含7,471个工具的统一语料库，我们在三个真实工具使用基准上评估SING。相比基线方法，SING将全局召回率@5提升最高59.8%，下游任务成功率提升最高28.9%，同时减少99.8%的全语料工具模式暴露，证明意图感知的图结构能在大规模智能体生态系统中实现更精准且上下文高效的工具发现。