Papers
arxiv:2603.07091

Exploring the Reasoning Depth of Small Language Models in Software Architecture: A Multidimensional Evaluation Framework Towards Software Engineering 2.0

Published on Mar 7
Authors:
,
,
,

Abstract

Small language models exhibit varying reasoning capabilities for software architecture tasks, with larger models showing better zero-shot performance while smaller models benefit more from fine-tuning, though semantic diversity can lead to hallucinations rather than productive exploration.

AI-generated summary

In the era of "Software Engineering 2.0" (SE 2.0), where intelligent agents collaborate with human engineers, Generative AI is advancing beyond code generation into Software Architecture (SA). While Large Language Models (LLMs) demonstrate superior capabilities, computational costs and data privacy concerns drive interest in Small Language Models (SLMs) with fewer than 7 billion parameters. However, the reasoning limits of these resource-constrained models remain unexplored. This study benchmarks 10 state-of-the-art SLMs on Architectural Decision Records generation, introducing a multi-dimensional framework evaluating Technical Compliance and Semantic Diversity. Our empirical results reveal a significant reasoning gap: models above the 3B-parameter threshold demonstrate robust zero-shot capabilities, while sub-2B models show the strongest BERTScore gains from Fine-Tuning, though compliance improvements are not guaranteed. Contrary to assumptions regarding context saturation, Few-Shot prompting serves as a highly effective calibration mechanism for select mid-sized models with short context windows. Furthermore, high semantic diversity in off-the-shelf small models often correlates with hallucination rather than productive exploration. These findings establish a rigorous baseline for deploying sustainable, locally hosted architectural assistants.

Community

Sign up or log in to comment

Get this paper in your agent:

hf papers read 2603.07091
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2603.07091 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2603.07091 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2603.07091 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.