交互式数字代理（IDAs）利用有状态数字环境的 API 来响应用户请求执行任务。虽然由指令微调的大型语言模型（LLMs）支持的 IDAs 可以在多步交互中对接口调用的反馈做出反应，但它们尚未在各自的数字环境中进行训练。以往方法在诸如 AppWorld 等复杂基准测试中完成的任务不足一半。我们提出了一个…
长提示对需要低延迟和有限资源操作的实际基于 LLM 的系统构成了重大挑战。我们研究零样本对话系统的提示压缩，该系统学习从文档中直接以内联方式使用未见过的 API，每个 API 可能占据数百个提示 token。我们从最近提出的一种方法（Mu 等，2023）开始，该方法学习将提示压缩为少量“要点…
我们的机器学习研究每天都在开辟新领域。
Environment-free Synthetic Data Generation for API-Calling Agents
Authors Seanie Lee, Sanjoy Chowdhury, Chao Jiang, Cheng-Yu Hsieh, Ting-Yao Hu, Alexander T Toshev, Oncel Tuzel, Raviteja Vemulapalli
View publication：https://arxiv.org/abs/2607.16900
Reinforcement Learning for Long-Horizon Interactive LLM Agents
February 5, 2025 research area Methods and Algorithms：/research/?domain=Methods%20and%20Algorithms
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
April 15, 2024 research area Speech and Natural Language Processing：/research/?domain=Speech%20and%20Natural%20Language%20Processing conference EACL：/research/?event=EACL
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…
Our research in machine learning breaks new ground every day.
情报判断
Aioga 编辑摘要
Aioga 编辑摘要：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。 Aioga 将其归入「论文研究」方向，重点关注它对真实使用和行业竞争的影响。
扫码直达文章详情