用模拟人机交互生成高质量多轮对话数据，提升智能体训练效果。
APIGen-MT: Agentic Pipeline for Multi-Turn Data Generation via Simulated Agent-Human Interplay
- 构建代理流水线，通过多轮反馈生成带真实动作的任务蓝图。
- 小模型在多轮任务中超越大模型，且多次测试结果更一致。
- 适合研究智能体训练、对话系统与自动化数据生成的团队。
训练高效多轮交互智能体需高质量数据以捕捉真实人机动态，但此类数据稀缺且人工收集成本高。我们提出APIGen-MT，一种两阶段框架，可生成可验证且多样化的多轮代理数据。第一阶段，基于多个大模型评审员与迭代反馈，生成包含真实动作的任务蓝图；第二阶段，通过模拟人机交互将蓝图转化为完整对话轨迹。我们训练了从10亿到700亿参数的xLAM-2-fc-r系列模型。实验表明，该系列模型在τ-bench和BFCL基准上优于GPT-4o和Claude 3.5，尤其在多轮场景中，小模型表现超过更大模型，且跨多次试验保持更高一致性。全面实验验证了‘蓝图到细节’方法生成高质量训练数据的有效性，推动更可靠、高效、强能力的智能体发展。我们开源了5000条合成数据轨迹及训练好的xLAM-2-fc-r模型，以促进智能体研究。
原文摘要 · Abstract (English)
Training effective AI agents for multi-turn interactions requires high-quality data that captures realistic human-agent dynamics, yet such data is scarce and expensive to collect manually. We introduce APIGen-MT, a two-phase framework that generates verifiable and diverse multi-turn agent data. In the first phase, our agentic pipeline produces detailed task blueprints with ground-truth actions, leveraging a committee of LLM reviewers and iterative feedback loops. These blueprints are then transformed into complete interaction trajectories through simulated human-agent interplay. We train a family of models -- the xLAM-2-fc-r series with sizes ranging from 1B to 70B parameters. Our models outperform frontier models such as GPT-4o and Claude 3.5 on $τ$-bench and BFCL benchmarks, with the smaller models surpassing their larger counterparts, particularly in multi-turn settings, while maintaining superior consistency across multiple trials. Comprehensive experiments demonstrate that our verified blueprint-to-details approach yields high-quality training data, enabling the development of more reliable, efficient, and capable agents. We open-source 5K synthetic data trajectories and the trained xLAM-2-fc-r models to advance research in AI agents. Models at https://huggingface.co/collections/Salesforce/xlam-2-67ef5be12949d8dcdae354c4; Dataset at https://huggingface.co/datasets/Salesforce/APIGen-MT-5k and Website at https://apigen-mt.github.io
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。