发表机构
Huawei Research（华为研究院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对多轮工具使用中参数级依赖被低估的问题，提出状态引导与参数溯源的数据合成方法SAP，构建SAP-4B模型，在多个基准上媲美更大模型。
AI 中文摘要
高质量的多轮工具使用数据对于训练智能体模型至关重要，然而现有的数据合成方法往往低估了参数级依赖关系，而这种依赖关系对于长时程工具使用至关重要。因此，即使模型选择了正确的工具，任务执行仍可能失败，因为模型填充的工具参数是基于虚构、过时或弱依据的值。为解决这一问题，我们提出了状态引导的参数溯源数据合成方法（SAP）。SAP结合了状态引导、工具参数溯源约束和轮次级验证，以高效构建具有长程依赖性和高准确性的工具使用轨迹。利用SAP生成的数据，我们构建了SAP-4B模型，该模型在多个基准测试中即使与更大的模型相比也极具竞争力。源代码、合成数据和训练权重可在以下网址获取：此https URL。
英文摘要
High-quality multi-turn tool-use data is essential for training agentic models, yet existing data synthesis methods often underrepresent the argument-level dependencies that are critical to long-horizon tool use. As a result, even when a model selects the correct tool, task execution may still fail because the model fills tool arguments with fabricated, stale, or weakly grounded values. To address this problem, we propose \textbf{State-Guided Data Synthesis with Argument Provenance (SAP)}. SAP combines state guidance, tool-argument provenance constraints, and turn-level validation to efficiently construct tool-use trajectories with long-range dependencies and high accuracy. Using data generated by SAP, we build SAP-4B, which is highly competitive even when compared with much larger models across multiple benchmarks. Source code, synthesized data, and trained weights are available at https://github.com/Zichen1024/SAP.
Comments23 pages, 3 figures, accepted by EMNLP 2026
