Initial Steps in Integrating Large Reasoning and Action Models for Service Composition
This work addresses service composition for adaptive software systems, presenting an incremental step by combining existing paradigms.
The paper tackles the challenge of service composition in software systems by integrating Large Reasoning Models (LRMs) and Large Action Models (LAMs) to bridge reasoning and execution gaps, proposing an architectural framework for automated service composition driven by natural language intent.
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.