Skip to content
Back to skills

Large Language Model As Metasurrogate For Datadriven Manytask Optimization A Proofofprinciple Study

ASecurity

**arXiv ID:** 2503.08301 **Authors:** Xian-Rong Zhang, Yue-Jiao Gong, Yuan-Ting Zhong, Ting Huang, Jun Zhang **Published:** 2025-03-11T11:13:11Z **Abstract:** In many-task optimization scenarios, surrogate models are valuable for mitigating the computational burden of repeated fitness evaluations across tasks. This study proposes a novel meta-surrogate framework to assist many-task optimization, by leveraging the knowledge transfer strengths and emergent capabilities of large language models ...

  • 3 stars
  • 0 votes
  • 0 copies
  • 5 views
  • Added September 11, 2026
toolsgoperformance

Security analysis

A100/100

Scanned September 11, 2026

npx -y skills add hiyenwong/ai_collection --skill large-language-model-as-metasurrogate-for-datadriven-manytask-optimization-a-proofofprinciple-study --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Large Language Model As Metasurrogate For Datadriven Manytask Optimization A Proofofprinciple Study?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Large Language Model As Metasurrogate For Datadriven Manytask Optimization A Proofofprinciple Study
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/hiyenwong-large-language-model-as-metasurrogate-for-datadriv/badge)](https://www.skillsdirectory.com/skills/hiyenwong-large-language-model-as-metasurrogate-for-datadriv)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
# Large Language Model as Meta-Surrogate for Data-Driven Many-Task Optimization: A Proof-of-Principle Study

**arXiv ID:** 2503.08301
**Authors:** Xian-Rong Zhang, Yue-Jiao Gong, Yuan-Ting Zhong, Ting Huang, Jun Zhang
**Published:** 2025-03-11T11:13:11Z
**Abstract:**
In many-task optimization scenarios, surrogate models are valuable for mitigating the computational burden of repeated fitness evaluations across tasks. This study proposes a novel meta-surrogate framework to assist many-task optimization, by leveraging the knowledge transfer strengths and emergent capabilities of large language models (LLMs). We formulate a unified framework for many-task fitness prediction, by defining a universal model with metadata to fit a group of problems. Fitness prediction is performed on metadata and decision variables, enabling efficient knowledge sharing across tasks and adaptability to new tasks. The LLM-based meta-surrogate treats fitness prediction as conditional probability estimation, employing a unified token sequence representation for task metadata, inputs, and outputs. This approach facilitates efficient inter-task knowledge sharing through shared token embeddings and captures complex task dependencies via multi-task model training. Experimental results demonstrate the model's emergent generalization ability, including zero-shot performance on problems with unseen dimensions. When integrated into evolutionary transfer optimization (ETO), our framework supports dual-level knowledge transfer -- at both the surrogate and individual levels -- enhancing optimization efficiency and robustness. This work establishes a novel foundation for applying LLMs in surrogate modeling, offering a versatile solution for many-task optimization.

## Skill Description

This skill is generated from the arXiv paper: Large Language Model as Meta-Surrogate for Data-Driven Many-Task Optimization: A Proof-of-Principle Study (2503.08301).

## How to Use

[To be filled in by the user or by future automation]

## References

- [arXiv:2503.08301](http://arxiv.org/abs/2503.08301v3)

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

View all in tools →

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.