用多智能体自动生成无限工具调用数据，让大模型自动进化。
Close the Loop: Synthesizing Infinite Tool-Use Data via Multi-Agent Role-Playing
- 三智能体协作模拟用户与工具交互，闭环生成高质量轨迹。
- 32B模型准确率从19.8%提升至70.9%，超10倍大的模型。
- 全程无需人工标注，适合想低成本训练智能体的开发者。
让大语言模型可靠调用外部工具仍是自主智能体的关键瓶颈。现有方法面临三大挑战：高质量轨迹依赖昂贵的人工标注、对未见工具泛化能力差、单模型合成存在固有质量上限，导致偏见与覆盖缺口持续存在。我们提出InfTool，一个完全自治的框架，通过自演化多智能体合成突破这些限制。仅需原始API规范，InfTool协调三个协作智能体（用户模拟器、工具调用助手、MCP服务器），生成涵盖单步调用到复杂多步流程的多样化、可验证轨迹。框架建立闭环：合成数据通过带门控奖励的组相对策略优化（GRPO）训练模型，改进后的模型生成更高质量数据以填补能力短板，循环迭代无须人工干预。在伯克利函数调用排行榜（BFCL）上的实验表明，InfTool将基础32B模型准确率从19.8%提升至70.9%（+258%），超越参数量10倍大的模型，媲美Claude-Opus，且全部基于合成数据，无需人工标注。
原文摘要 · Abstract (English)
Enabling Large Language Models (LLMs) to reliably invoke external tools remains a critical bottleneck for autonomous agents. Existing approaches suffer from three fundamental challenges: expensive human annotation for high-quality trajectories, poor generalization to unseen tools, and quality ceilings inherent in single-model synthesis that perpetuate biases and coverage gaps. We introduce InfTool, a fully autonomous framework that breaks these barriers through self-evolving multi-agent synthesis. Given only raw API specifications, InfTool orchestrates three collaborative agents (User Simulator, Tool-Calling Assistant, and MCP Server) to generate diverse, verified trajectories spanning single-turn calls to complex multi-step workflows. The framework establishes a closed loop: synthesized data trains the model via Group Relative Policy Optimization (GRPO) with gated rewards, the improved model generates higher-quality data targeting capability gaps, and this cycle iterates without human intervention. Experiments on the Berkeley Function-Calling Leaderboard (BFCL) demonstrate that InfTool transforms a base 32B model from 19.8% to 70.9% accuracy (+258%), surpassing models 10x larger and rivaling Claude-Opus, and entirely from synthetic data without human annotation.
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。