[论文] Scaling Laws for Tool-Use Agents via Controllable Environment Synthesi...

论文概要

研究领域: ML / 工具使用 作者: Andrew Szot, Samira Abnar, Omar Attia, Abbas Kazerouni, Michael Kirchhof, Cheng-Yu Hsieh, Raviteja Vemulapalli, Alexander Toshev 发布时间: 2026-10-27 arXiv: 2610.37648

中文摘要

本文研究如何构建能完成复杂多步任务的高性能LLM工具使用智能体，重点研究合成工具使用环境中数据组成如何影响智能体训练。提出SynthAPI管线，沿工具、任务和数据库三个轴显式控制生成环境的多样性。通过在458,752个任务上系统变化生成控制参数，训练849个不同规模的模型，推导出预测下游工具使用智能体泛化能力的scaling law。这些可预测的关系揭示了扩展工具使用智能体数据的几条经验：随着数据预算增长，扩展工具和数据库多样性比增加任务数量更有效；增加数据复杂度带来更大收益。按照这些发现进行扩展，训练出的智能体在四个评估基准上均优于先前工作训练的模型。

原文摘要

We explore how to build performant large language model (LLM) tool-use agents that complete complex, multi-step tasks. Specifically, we study how data composition in synthetically generated tool-use environments affects the training of such agents. To do so, we propose the SynthAPI pipeline, which explicitly controls the diversity of generated environments along the axes of tools, tasks, and the databases on which the tools operate. By systematically varying SynthAPI's generation controls in 458,752 tasks across 849 trained models of four different sizes, we derive a scaling law that predicts downstream tool-use agent generalization based on the scale and composition of the synthesized environments. These predictable relationships reveal several lessons for scaling tool-use agent data. As data budgets grow, scaling tool and database diversity becomes more effective than increasing the number of tasks, and increasing data complexity yields larger gains. Scaling according to these findings yields agents that outperform models trained on data from prior work in large-scale tool-use agent and synthetic environment generation across four evaluation benchmarks.

---

*自动采集于 2026-10-29*

#论文 #arXiv #AI #小凯