# Apple 提出无环境合成数据生成方法，用于训练 API 调用型 LLM 智能体

- 来源：Apple Machine Learning Research（RSS）
- 发布时间：2026-07-21 08:00
- AIHOT 分数：52
- AIHOT 链接：https://aihot.virxact.com/items/cmrurrjvx04zdbi9t9c30lp8p
- 原文链接：https://machinelearning.apple.com/research/environment-free

## AI 摘要

Apple 研究人员提出一种无需可执行环境即可生成高质量训练数据的方法，用于训练 API 调用型大语言模型（LLM）智能体。该方法仅需 API 规格说明，利用 LLM 作为数字世界模型，通过教师智能体与 LLM 模拟器交互生成轨迹，并由 LLM 裁判过滤。在 AppWorld 和 OfficeBench 基准上，微调模型使用该合成数据取得了显著的性能提升。

## 正文

AuthorsSeanie Lee, Sanjoy Chowdhury, Chao Jiang, Cheng-Yu Hsieh, Ting-Yao Hu, Alexander T Toshev, Oncel Tuzel, Raviteja Vemulapalli

Training API-calling large language model (LLM) agents demands massive amounts of high-quality trajectories. However, collecting such data at scale typically requires fully implemented environments with executable APIs and realistic, pre-populated backend databases, creating a major bottleneck for scalability. To overcome this, we propose an environment-free synthetic data generation approach that leverages LLMs as on-the-fly digital world models. Given only API specifications, our method generates trajectories mimicking interactions between an agent and a stateful environment. Specifically, an LLM first generates diverse tasks solvable with the provided APIs. A teacher agent then iteratively solves each task while an LLM simulator generates coherent synthetic API responses conditioned on the task context and simulation history. Finally, an LLM judge filters the trajectories to ensure the quality of the resulting dataset. We evaluate our approach on the challenging AppWorld and OfficeBench benchmarks, which include both information-retrieval and state-changing tasks. Fine-tuning models on our synthetic data yields significant performance gains, demonstrating that effective supervision for API-calling agents can be generated without any executable environment. Our results establish LLM-based API simulation as a practical, scalable solution for training agents across diverse API ecosystems.

Related readings and updates.

Reinforcement Learning for Long-Horizon Interactive LLM Agents

February 5, 2025research area Methods and Algorithms

Interactive digital agents (IDAs) leverage APIs of stateful digital environments to perform tasks in response to user requests. While IDAs powered by instruction-tuned large language models (LLMs) can react to feedback from interface invocations in multi-step exchanges, they have not been trained in their respective digital environments. Prior methods accomplish less than half of tasks in sophisticated benchmarks such as AppWorld. We present a…

Hierarchical and Dynamic Prompt Compression for Efficient Zero-shot API Usage

Long prompts present a significant challenge for practical LLM-based systems that need to operate with low latency and limited resources. We investigate prompt compression for zero-shot dialogue systems that learn to use unseen APIs directly in-context from their documentation, which may take up hundreds of prompt tokens per API. We start from a recently introduced approach (Mu et al., 2023) that learns to compress the prompt into a few “gist…

Discover opportunities in Machine Learning.