Initial Steps in Integrating Large Reasoning and Action Models for Service Composition

TL;DR

This paper proposes an integrated framework combining Large Reasoning Models and Large Action Models to improve automated service composition by enabling reasoning about requirements and dynamic execution of workflows.

Contribution

It introduces a novel architectural framework that unites LRMs and LAMs, addressing their individual limitations for more effective service composition.

Findings

Framework enables reasoning about service constraints

System supports dynamic execution of workflows

Potential to automate service composition fully

Abstract

Service composition remains a central challenge in building adaptive and intelligent software systems, often constrained by limited reasoning capabilities or brittle execution mechanisms. This paper explores the integration of two emerging paradigms enabled by large language models: Large Reasoning Models (LRMs) and Large Action Models (LAMs). We argue that LRMs address the challenges of semantic reasoning and ecosystem complexity while LAMs excel in dynamic action execution and system interoperability. However, each paradigm has complementary limitations - LRMs lack grounded action capabilities, and LAMs often struggle with deep reasoning. We propose an integrated LRM-LAM architectural framework as a promising direction for advancing automated service composition. Such a system can reason about service requirements and constraints while dynamically executing workflows, thus bridging the gap between intention and execution. This integration has the potential to transform service composition into a fully automated, user-friendly process driven by high-level natural language intent.