[2603.24647] Can LLMs Beat Classical Hyperparameter Optimization Algorithms? A Study on autoresearch

-->

Computer Science > Machine Learning

arXiv:2603.24647 (cs)

[Submitted on 25 Mar 2026 (v1), last revised 17 Apr 2026 (this version, v5)]

Title:Can LLMs Beat Classical Hyperparameter Optimization Algorithms? A Study on autoresearch

Authors:Fabio Ferreira, Lucca Wobbe, Arjun Krishnakumar, Frank Hutter, Arber Zela<br>View a PDF of the paper titled Can LLMs Beat Classical Hyperparameter Optimization Algorithms? A Study on autoresearch, by Fabio Ferreira and 4 other authors

View PDF<br>HTML (experimental)

Abstract:The autoresearch repository enables an LLM agent to optimize hyperparameters by editing training code directly. We use it as a testbed to compare classical HPO algorithms against LLM-based methods on tuning the hyperparameters of a small language model under a fixed compute budget. When defining a fixed search space over autoresearch, classical methods such as CMA-ES and TPE consistently outperform LLM-based agents, where avoiding out-of-memory failures matters more than search diversity. Allowing the LLM to directly edit source code narrows the gap to the classical methods but does not close it, even with frontier models available at the time of writing such as Claude Opus 4.6 and Gemini 3.1 Pro Preview. We observe that LLMs struggle to track optimization state across trials. In contrast, classical methods lack the domain knowledge of LLMs. To combine the strengths of both, we introduce Centaur, a hybrid that shares CMA-ES's interpretable internal state, including mean vector, step-size, and covariance matrix, with an LLM. Centaur achieves the best result in our experiments, and a 0.8B LLM already suffices to outperform all classical and pure LLM methods. Unconstrained code editing requires larger models to be competitive with classical methods. We further analyze search diversity, model scaling from 0.8B to frontier models, and ablate the fraction of LLM-proposed trials in Centaur. All in all, our results suggest that LLMs are most effective as a complement to classical optimizers, not as a replacement.

Code is available at this https URL & interactive demo at this https URL.

Subjects:

Machine Learning (cs.LG); Machine Learning (stat.ML)

Cite as:<br>arXiv:2603.24647 [cs.LG]

(or<br>arXiv:2603.24647v5 [cs.LG] for this version)

https://doi.org/10.48550/arXiv.2603.24647

Focus to learn more

arXiv-issued DOI via DataCite

Submission history<br>From: Fabio Ferreira [view email]<br>[v1]<br>Wed, 25 Mar 2026 17:29:40 UTC (1,874 KB)

[v2]<br>Sun, 29 Mar 2026 18:46:53 UTC (2,456 KB)

[v3]<br>Sat, 4 Apr 2026 10:33:34 UTC (3,843 KB)

[v4]<br>Mon, 13 Apr 2026 21:59:37 UTC (3,768 KB)

[v5]<br>Fri, 17 Apr 2026 18:50:51 UTC (3,905 KB)

Full-text links:<br>Access Paper:

View a PDF of the paper titled Can LLMs Beat Classical Hyperparameter Optimization Algorithms? A Study on autoresearch, by Fabio Ferreira and 4 other authors<br>View PDF<br>HTML (experimental)<br>TeX Source

view license

Current browse context:

cs.LG

next >

new<br>recent<br>| 2026-03

Change to browse by:

cs<br>stat<br>stat.ML

References & Citations

NASA ADS<br>Google Scholar

Semantic Scholar

export BibTeX citation<br>Loading...

BibTeX formatted citation

&times;

loading...

Data provided by:

Bookmark

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

IArxiv recommender toggle

IArxiv Recommender<br>(What is IArxiv?)

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...