arXiv：cs.AI· Guangyu Feng, Huanzhi Mao, Prabal Dutta, Joseph E. Gonzalez·· 20 小时前
AsyncFC：无需改动模型的 LLM 异步函数调用框架
Concurrency without Model Changes: Future-based Asynchronous Function Calling for LLMs
AI 导读
AsyncFC 是一个纯执行层框架，将 LLM 解码与函数执行解耦，在依赖允许时实现模型解码与函数执行的 overlap 以及函数间并行。它叠加在现有模型和未经修改的函数实现之上，无需微调、也无需改动标准同步函数调用协议。在编程任务上，AsyncFC 取得 1.4 倍端到端加速并保持任务准确率，还显示 LLM 具备对表示未完成执行结果的 symbolic futures 进行推理的原生能力。
正文
Abstract:Function calling, also known as tool use, is a core capability of modern LLM agents but is typically constrained by synchronous execution semantics. Under these semantics, LLM decoding is blocked until each function call completes, resulting in increasing end-to-end latency. In this work, we introduce AsyncFC, a pure execution-layer framework that decouples LLM decoding from function execution, enabling overlap between model decoding and function execution as well as inter-function parallelism when dependencies permit. AsyncFC layers over existing models and unmodified function implementations, requiring no fine-tuning or changes to the standard synchronous function-calling protocol. On coding tasks, AsyncFC achieves a $1.4\times$ end-to-end speedup while preserving task accuracy. Furthermore, these results reveal that LLMs possess a native capability to reason over symbolic futures that represent unresolved execution results, enabling an asynchronous paradigm for model-tool interaction.
| Subjects: | Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Machine Learning (cs.LG) |
| Cite as: | arXiv:2605.15077 [cs.CL] |
| (or arXiv:2605.15077v2 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2605.15077 arXiv-issued DOI via DataCite |
Submission history
From: Guangyu Feng [view email]
[v1]
Thu, 14 May 2026 17:02:28 UTC (1,121 KB)
[v2]
Fri, 9 Oct 2026 21:26:40 UTC (1,121 KB)
来源：arXiv：cs.AI · arxiv.org