Conference paper · 2025 · Open access

CALM: Co-evolution of Algorithms and Language Model for Automatic Heuristic Design

Huang, Ziyao, Weiwei Wu, Kui Wu, Wang, Jianping, Wei‐Bin Lee

International Conference on Learning Representations · Published 18 May 2025 · DOI 10.48550/arxiv.2505.12285

Open PDFView at the publisherCite this paper

In brief

“CALM: Co-evolution of Algorithms and Language Model for Automatic Heuristic Design” is a 2025 conference paper by Huang, Ziyao and 4 co-authors, published in International Conference on Learning Representations. OpenAlex counts 39 citations as of 21 November 2026, which puts it in the top 2% of works published in 2025 by citations. It is open access: the full text is free to read at International Conference on Learning Representations.

Citations
39
Most cited in
2026 (32)
Field-weighted impact
7.54
References
52
Authors
5

Abstract

Tackling complex optimization problems often relies on expert-designed heuristics, typically crafted through extensive trial and error. Recent advances demonstrate that large language models (LLMs), when integrated into well-designed evolutionary search frameworks, can autonomously discover high-performing heuristics at a fraction of the traditional cost. However, existing approaches predominantly rely on verbal guidance, i.e., manipulating the prompt generation process, to steer the evolution of heuristics, without adapting the underlying LLM. We propose a hybrid framework that combines verbal and numerical guidance, the latter achieved by fine-tuning the LLM via reinforcement learning based on the quality of generated heuristics. This joint optimization allows the LLM to co-evolve with the search process. Our method outperforms state-of-the-art (SOTA) baselines across various optimization tasks, running locally on a single 24GB GPU using a 7B model with INT4 quantization. It surpasses methods that rely solely on verbal guidance, even when those use significantly more powerful API-based models.

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

Ziyao, H., Wu, W., Wu, K., Jianping, W., & Lee, W. (2025). CALM: Co-evolution of Algorithms and Language Model for Automatic Heuristic Design. International Conference on Learning Representations. https://doi.org/10.48550/arxiv.2505.12285

MLA 9

Ziyao, Huang,, et al. “CALM: Co-evolution of Algorithms and Language Model for Automatic Heuristic Design.” International Conference on Learning Representations, 2025. https://doi.org/10.48550/arxiv.2505.12285.

Chicago

Ziyao, Huang,, Weiwei Wu, Kui Wu, Wang, Jianping, and Wei‐Bin Lee. 2025. “CALM: Co-evolution of Algorithms and Language Model for Automatic Heuristic Design.” International Conference on Learning Representations. https://doi.org/10.48550/arxiv.2505.12285.

Harvard

Ziyao, H. et al. (2025) ‘CALM: Co-evolution of Algorithms and Language Model for Automatic Heuristic Design’, International Conference on Learning Representations. doi:10.48550/arxiv.2505.12285.

IEEE

H. Ziyao, W. Wu, K. Wu, W. Jianping, and W. Lee, “CALM: Co-evolution of Algorithms and Language Model for Automatic Heuristic Design,” International Conference on Learning Representations, 2025, doi: 10.48550/arxiv.2505.12285.

BibTeX

@inproceedings{ziyao2025calm,
  title     = {{CALM: Co-evolution of Algorithms and Language Model for Automatic Heuristic Design}},
  author    = {Ziyao, Huang, and Wu, Weiwei and Wu, Kui and Jianping, Wang, and Lee, Wei‐Bin},
  booktitle = {International Conference on Learning Representations},
  year      = {2025},
  doi       = {10.48550/arxiv.2505.12285},
  url       = {https://doi.org/10.48550/arxiv.2505.12285}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Topic and keywords

Physical Sciences › Computer Science › Artificial Intelligence › Metaheuristic Optimization Algorithms Research

  • large language models
  • reinforcement learning fine-tuning
  • evolutionary search
  • verbal guidance
  • combinatorial optimization
  • prompt engineering

Work with this paper

Most-cited papers in Computer Science

All highly cited Computer Science papers

Questions about this paper

How do I cite this paper in APA style?

Ziyao, H., Wu, W., Wu, K., Jianping, W., & Lee, W. (2025). CALM: Co-evolution of Algorithms and Language Model for Automatic Heuristic Design. International Conference on Learning Representations. https://doi.org/10.48550/arxiv.2505.12285

How many times has this paper been cited?

39 times, according to OpenAlex on 21 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.

Is this paper free to read?

Yes. It is open access at International Conference on Learning Representations: sign in and open the PDF from this page.

Who wrote this paper?

Huang, Ziyao, Weiwei Wu, Kui Wu, Wang, Jianping, Wei‐Bin Lee.

What is the DOI of this paper?

10.48550/arxiv.2505.12285, permanently at https://doi.org/10.48550/arxiv.2505.12285. Sign in and open it from this page.

Bibliographic data from OpenAlex (CC0), last checked 21 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.