让大模型用代码块一次性调用多个工具，提升复杂任务准确率。
HyperTool: Beyond Step-Wise Tool Calls for Tool-Augmented Agents
- 用代码块封装工具调用与数据处理，减少模型在推理中暴露的细粒度操作。
- 在MCP-Universe上，Qwen3-32B准确率从15.69%提升至35.29%，性能超越GPT-OSS和Kimi-k2.5。
- 适合需要多步工具协同的智能体开发，尤其对长链任务优化明显。
工具增强型大模型智能体通常依赖逐步原子化工具调用，每次调用、观察和值传递都显式暴露在主推理轨迹中，造成执行粒度不匹配：局部确定性工具流程被展开为重复的模型可见决策，消耗上下文并迫使模型管理低层级数据流。我们提出超工具接口 HyperTool，一种统一的可执行 MCP 风格工具接口，改变了模型可见的工具执行单元。模型通过一个代码块调用 HyperTool，可使用原有工具模式调用工具、操作返回值并本地传递中间结果，将确定性工具子程序折叠为单次外部调用。为训练模型使用该接口，我们从跨工具组合任务中合成 HyperTool 格式轨迹，并在真实 MCP 环境中验证。在 MCP-Universe 上，HyperTool 将 Qwen3-32B 平均准确率从 15.69% 提升至 35.29%，将 Qwen3-8B 从 9.93% 提升至 33.33%，且平均准确率超过 GPT-OSS 与 Kimi-k2.5，表明 HyperTool 能显著提升多步工具使用能力。
原文摘要 · Abstract (English)
Tool-augmented LLM agents commonly rely on step-wise atomic tool calls, where each invocation, observation, and value transfer is exposed in the main reasoning trace. This creates an \emph{execution-granularity mismatch}: locally deterministic tool workflows are unfolded into repeated model-visible decisions, consuming context and forcing the model to manage low-level dataflow in the trace. We introduce \textbf{HyperTool}, a unified executable MCP-style tool interface that changes the model-visible unit of tool execution. A model invokes HyperTool with a code block that can call existing tools through their original schemas, manipulate returned values, and pass intermediate results locally, folding deterministic tool subroutines into a single outer call. To train models to use this interface, we synthesize HyperTool-format trajectories from cross-tool compositional tasks and verify them in real MCP environments. On MCP-Universe, HyperTool improves average accuracy from 15.69\% to 35.29\% on Qwen3-32B and from 9.93\% to 33.33\% on Qwen3-8B, and surpass GPT-OSS and Kimi-k2.5 on average accuracy, showing that our HyperTool can substantially improve multi-step tool use.
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。