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）智能体日益依赖管理上下文、工具与多轮执行的智能体框架，使工具成为在真实数字环境中行动的核心接口。当接入框架的工具生态扩展至数百甚至数千个API、服务和任务特定技能时，穷举式工具模式注入成本高昂，且强加了封闭世界假设，将智能体限制在预定义的静态库存中。检索增强型工具选择提供了一种自然替代方案，但现有的一次性检索方法往往难以将孤立的工具描述与智能体的真实任务意图对齐，尤其是在长程任务中——所需能力需通过任务分解、观察和新增子目标逐步显现。我们提出SING，一种意图感知的主动工具发现框架，构建了连接用户意图、工具能力与工具协作模式的意图-工具图，并根据演进的任务状态动态检索工具。基于包含7,471个工具的统语料库，我们在三个真实工具使用基准上评估了SING。相较基线方法，SING将全局召回率@5提升高达59.8%，下游任务成功率提升高达28.9%，同时将全语料工具模式暴露量减少99.8%，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。