---
id: 20261114-T0-07
title: "ToolTurns：多轮对话中的LLM智能体工具使用基准"
title_en: "ToolTurns: Benchmarking LLM Agents' Tool Use in Multi-Turn Dialogue"
url: https://ai.daily.yangsir.net/daily/20261114-T0-07
issue_date: 2026-11-14
publish_date: 2026-11-13T05:00:00.000Z
category: research
source_name: "arXiv cs.CL (NLP)"
source_url: https://arxiv.org/abs/2611.14925
---

# ToolTurns：多轮对话中的LLM智能体工具使用基准

研究者推出ToolTurns基准，用于评测工具调用型语言模型在多轮对话中的表现。现有大规模工具使用基准多聚焦孤立请求，ToolTurns包含2620道题，覆盖1827个工具和11004个API端点，横跨多轮交互场景。该基准填补了对话式工具调用评测的空白，可用于衡量模型在多轮对话中维持工具调用上下文的能力。

## English Version

**ToolTurns: Benchmarking LLM Agents' Tool Use in Multi-Turn Dialogue**

Researchers introduced ToolTurns, a benchmark for evaluating tool-using language models in multi-turn dialogue. Existing large-scale tool-use benchmarks mostly focus on isolated requests; ToolTurns contains 2,620 problems spanning 1,827 tools and 11,004 API endpoints across multi-turn interactions. The benchmark fills a gap in evaluating conversational tool use and can measure how well models maintain tool-calling context across turns.

---

**来源**：[arXiv cs.CL (NLP)](https://arxiv.org/abs/2611.14925)

**详情页**：https://ai.daily.yangsir.net/daily/20261114-T0-07

---

*智语观潮 · Daily — https://ai.daily.yangsir.net/llms.txt*