Efficient Function Orchestration for Large Language Models

Xiaoxia Liu

doi:10.1109/TSE.2025.3619112

Efficient Function Orchestration for Large Language Models

2025-10-09

0

PRE

AI

DOI：10.1109/TSE.2025.3619112

Original

Original request for help

Save

Abstract

En 中文

Function calling is a fundamental capability of today’s large language models, but sequential function calling posed efficiency problems. Recent studies have proposed to request function calls with parallelism support in order to alleviate this issue. However, they either delegate the concurrent function calls to users for execution which are conversely executed sequentially, or overlook the relations among various function calls, rending limited efficiency. This paper introduces LLMOrch, an advanced framework for automated, parallel function calling in large language models. The key principle behind LLMOrch is to identify an available processor to execute a function call while preventing any single processor from becoming overburdened. To this end, LLMOrch models the data relations (i.e., definition-use (def-use) dependencies among different function calls and coordinates their executions by their contro l relations (i.e., mutual-exclusion) as well as the working status of the underlying processors. When comparing with state-of-the-art techniques, LLMOrch demonstrated comparable efficiency improvements in orchestrating I/O-intensive functions, while significantly outperforming (2$\times$) them with compute-intensive functions. LLMOrch’s performance even showed a linear correlation to the number of allocated processors. We believe that these results highlight the potential of LLMOrch as an efficient solution for parallel function orchestration in the context of large language models.

Keywords:

Large language models

function call

parallel function call

Efficient Function Orchestration for Large Language Models

Abstract

Journal

Organization

Cited Papers