Computer Science > Artificial Intelligence
arXiv:2506.02153 (cs)
Submitted on 2 Jun 2025 ([v1), last revised 15 Sep 2025 (this version, v2)]
Title:Small Language Models are the Future of Agentic AI
Authors:Peter Belcak, Greg Heinrich, Shizhe Diao, Yonggan Fu, Xin Dong, Saurav Muralidharan, Yingyan Celine Lin, Pavlo Molchanov
View a PDF of the paper titled Small Language Models are the Future of Agentic AI, by Peter Belcak and 7 other authors
View PDF
HTML (experimental)
Abstract:
Large language models (LLMs) are often praised for exhibiting near-human performance on a wide range of tasks and valued for their ability to hold a general conversation. The rise of agentic AI systems is, however, ushering in a mass of applications in which language models perform a small number of specialized tasks repetitively and with little variation.
Here we lay out the position that small language models (SLMs) are sufficiently powerful, inherently more suitable, and necessarily more economical for many invocations in agentic systems, and are therefore the future of agentic AI. Our argumentation is grounded in the current level of capabilities exhibited by SLMs, the common architectures of agentic systems, and the economy of LM deployment. We further argue that in situations where general-purpose conversational abilities are essential, heterogeneous agentic systems (i.e., agents invoking multiple different models) are the natural choice. We discuss the potential barriers for the adoption of SLMs in agentic systems and outline a general LLM-to-SLM agent conversion algorithm.
Our position, formulated as a value statement, highlights the significance of the operational and economic impact even a partial shift from LLMs to SLMs is to have on the AI agent industry. We aim to stimulate the discussion on the effective use of AI resources and hope to advance the efforts to lower the costs of AI of the present day. Calling for both contributions to and critique of our position, we commit to publishing all such correspondence at
this https URL
.
| Subjects: | Artificial Intelligence (cs.AI) |
|---|---|
| Cite as: | arXiv:2506.02153 [cs.AI] |
| (or arXiv:2506.02153v2 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2506.02153 arXiv-issued DOI via DataCite |
Submission history
From: Peter Belcak [
view email
]
[v1]
Mon, 2 Jun 2025 18:35:16 UTC (132 KB)
[v2]
Mon, 15 Sep 2025 22:15:00 UTC (490 KB)
Full-text links:
Access Paper:
[imagen: license icon view license](http://creativecommons.org/licenses/by/4.0/)
Current browse context:
cs.AI
Change to browse by:
References & Citations
Loading...
BibTeX formatted citation
loading...
Data provided by:
Bookmark
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer ([What is the Explorer?](https://info.arxiv.org/labs/showcase.html#arxiv-bibliographic-explorer))
Connected Papers Toggle
Connected Papers ([What is Connected Papers?](https://www.connectedpapers.com/about))
Litmaps Toggle
Litmaps ([What is Litmaps?](https://www.litmaps.co/))
scite.ai Toggle
scite Smart Citations ([What are Smart Citations?](https://www.scite.ai/))
Code, Data, Media
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv ([What is alphaXiv?](https://alphaxiv.org/))
Links to Code Toggle
CatalyzeX Code Finder for Papers ([What is CatalyzeX?](https://www.catalyzex.com))
DagsHub Toggle
DagsHub ([What is DagsHub?](https://dagshub.com/))
GotitPub Toggle
Gotit.pub ([What is GotitPub?](http://gotit.pub/faq))
Huggingface Toggle
Hugging Face ([What is Huggingface?](https://huggingface.co/huggingface))
ScienceCast Toggle
ScienceCast ([What is ScienceCast?](https://sciencecast.org/welcome))
Demos
Demos
Replicate Toggle
Replicate ([What is Replicate?](https://replicate.com/docs/arxiv/about))
Spaces Toggle
Hugging Face Spaces ([What is Spaces?](https://huggingface.co/docs/hub/spaces))
Spaces Toggle
TXYZ.AI ([What is TXYZ.AI?](https://txyz.ai))
Related Papers
Recommenders and Search Tools
Link to Influence Flower
Influence Flower ([What are Influence Flowers?](https://influencemap.cmlab.dev/))
Core recommender toggle
CORE Recommender ([What is CORE?](https://core.ac.uk/services/recommender))
- Author
- Venue
- Institution
- Topic
About arXivLabs
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? **Learn more about arXivLabs**.
Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)