# Large Language Model as Meta-Surrogate for Data-Driven Many-Task Optimization: A Proof-of-Principle Study

arXiv: https://arxiv.org/abs/2503.08301 · HTML: https://mlsanity.com/paper/2503.08301/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 46 references that are in the map.
- First posted on arXiv 11 Mar 2025.

## Builds on (most cited first, 15 of 15)

- [Fine-Tuning Language Models from Human Preferences](https://mlsanity.com/paper/1909.08593/) (2019)
- [Large Language Models Encode Clinical Knowledge](https://mlsanity.com/paper/2212.13138/) (2022)
- [Competition-Level Code Generation with AlphaCode](https://mlsanity.com/paper/2203.07814/) (2022)
- [Solving Quantitative Reasoning Problems with Language Models](https://mlsanity.com/paper/2206.14858/) (2022)
- [Revisiting Deep Learning Models for Tabular Data](https://mlsanity.com/paper/2106.11959/) (2021)
- [TabPFN: A Transformer That Solves Small Tabular Classification Problems in a Second](https://mlsanity.com/paper/2207.01848/) (2022)
- [Deep Evidential Regression](https://mlsanity.com/paper/1910.02600/) (2019)
- [SAINT: Improved Neural Networks for Tabular Data via Row Attention and Contrastive Pre-Training](https://mlsanity.com/paper/2106.01342/) (2021)
- [COCO: A Platform for Comparing Continuous Optimizers in a Black-Box Setting](https://mlsanity.com/paper/1603.08785/) (2016)
- [Data-Driven Offline Optimization For Architecting Hardware Accelerators](https://mlsanity.com/paper/2110.11346/) (2021)
- [Evolutionary Multitasking for Single-objective Continuous Optimization: Benchmark Problems, Performance Metric, and Baseline Results](https://mlsanity.com/paper/1706.03470/) (2017)
- [Scaling Gaussian Processes for Learning Curve Prediction via Latent Kronecker Structure](https://mlsanity.com/paper/2410.09239/) (2024)
- [Offline Contextual Bayesian Optimization for Nuclear Fusion](https://mlsanity.com/paper/2001.01793/) (2020)
- [Learning Multi-Task Gaussian Process Over Heterogeneous Input Domains](https://mlsanity.com/paper/2202.12636/) (2022)
- [Bayesian Inverse Transfer in Evolutionary Multiobjective Optimization](https://mlsanity.com/paper/2312.14713/) (2023)

## Built on by (most cited first, 1 of 1)

- [In-Context Guidance: Learning Inter-Task Synergies via Numerical Foundational Models for Few-Shot Multitask Optimization](https://mlsanity.com/paper/2609.25836/) (2026)

## Abstract (arXiv)

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.