无需人工标注，让开源大模型学会复杂工具使用。
GOAT: A Training Framework for Goal-Oriented Agent with Tools
- 基于API文档自动生成带目标的调用数据，实现无监督训练。
- 在多个基准上达到顶尖表现，超越现有开源模型。
- 适合想构建强推理能力开源智能体的研究者与开发者。
当前方法因缺乏训练数据而依赖零样本评估；尽管闭源模型如GPT-4具备强大推理能力，但小型开源模型在复杂工具使用上仍表现不佳。为此，我们提出新型训练框架GOAT，可在无需人工标注的情况下微调大语言模型（LLM）代理。GOAT利用创新的“调用优先”生成范式，从API文档自动合成目标导向的API执行数据，依据实际调用序列构建训练集。通过大量实验，我们证明经GOAT训练的代理在多个现有目标导向基准上达到当前最优性能。此外，我们引入GOATBench——一个全新的目标导向API执行基准，并验证使用GOAT训练的代理在此设置下同样表现出色。这些结果表明，GOAT为构建具备复杂推理与工具使用能力的鲁棒开源大模型代理提供了可行路径。
原文摘要 · Abstract (English)
Current approaches rely on zero-shot evaluation due to the absence of training data; while proprietary models such as GPT-4 exhibit strong reasoning capabilities, smaller open-source models remain ineffective at complex tool use. To address this limitation, we propose a novel training framework GOAT, that enables fine-tuning LLM agents without human annotation. GOAT automatically synthesizes goal-oriented API execution data from API documents using a novel call-first generation paradigm, that constructs training data based on executed API call sequences. Through extensive experiments, we show that GOAT-trained agents achieve state-of-the-art performance across multiple existing goal-oriented benchmarks. In addition, we introduce GOATBench, a new goal-oriented API execution benchmark, and demonstrate that agents trained with GOAT also excel in this setting. These results highlight GOAT as a practical path toward building robust open-source LLM agents capable of complex reasoning and 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。