# Beyond Average Performance: Dynamic Instance Clustering and Specialized Algorithm Design in LLM-Assisted Evolutionary Search

arXiv: https://arxiv.org/abs/2608.03129 · HTML: https://mlsanity.com/paper/2608.03129/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 51 references that are in the map.
- First posted on arXiv 4 Aug 2026.

## Builds on (most cited first, 19 of 19)

- [Automated Design of Agentic Systems](https://mlsanity.com/paper/2408.08435/) (2024)
- [ReEvo: Large Language Models as Hyper-Heuristics with Reflective Evolution](https://mlsanity.com/paper/2402.01145/) (2024)
- [Evolution of Heuristics: Towards Efficient Automatic Algorithm Design Using Large Language Model](https://mlsanity.com/paper/2401.02051/) (2024)
- [LLM-SR: Scientific Equation Discovery via Programming with Large Language Models](https://mlsanity.com/paper/2404.18400/) (2024)
- [Monte Carlo Tree Search for Comprehensive Exploration in LLM-Based Automatic Heuristic Design](https://mlsanity.com/paper/2501.08603/) (2025)
- [LLaMEA: A Large Language Model Evolutionary Algorithm for Automatically Generating Metaheuristics](https://mlsanity.com/paper/2405.20132/) (2024)
- [HSEvo: Elevating Automatic Heuristic Design with Diversity-Driven Harmony Search and Genetic Algorithm Using LLMs](https://mlsanity.com/paper/2412.14995/) (2024)
- [A Systematic Survey on Large Language Models for Algorithm Design](https://mlsanity.com/paper/2410.14716/) (2024)
- [Multi-objective Evolution of Heuristic Using Large Language Model](https://mlsanity.com/paper/2409.16867/) (2024)
- [Algorithm Evolution Using Large Language Model](https://mlsanity.com/paper/2311.15249/) (2023)
- [EoH-S: Evolution of Heuristic Set using LLMs for Automated Heuristic Design](https://mlsanity.com/paper/2508.03082/) (2025)
- [LLM4AD: A Platform for Algorithm Design with Large Language Model](https://mlsanity.com/paper/2412.17287/) (2024)
- [Design Principle Transfer in Neural Architecture Search via Large Language Models](https://mlsanity.com/paper/2408.11330/) (2024)
- [LLM-Driven Instance-Specific Heuristic Generation and Selection](https://mlsanity.com/paper/2506.00490/) (2025)
- [Automatic Construction of Parallel Portfolios via Explicit Instance Grouping](https://mlsanity.com/paper/1804.06088/) (2018)
- [Multimodal LLM-assisted Evolutionary Search for Programmatic Control Policies](https://mlsanity.com/paper/2508.05433/) (2025)
- [AutoSGNN: Automatic Propagation Mechanism Discovery for Spectral Graph Neural Networks](https://mlsanity.com/paper/2412.12483/) (2024)
- [Discovering Heuristics with Large Language Models (LLMs) for Mixed-Integer Programs: Single-Machine Scheduling](https://mlsanity.com/paper/2510.24013/) (2025)
- [Solving The Lunar Lander Problem under Uncertainty using Reinforcement Learning](https://mlsanity.com/paper/2011.11850/) (2020)

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

- [Multi-Task Evolution for Zero-Shot Cross-Problem Generalization using LLMs](https://mlsanity.com/paper/2610.03316/) (2026)

## Abstract (arXiv)

Large Language Model-assisted Evolutionary Search (LES) has emerged as a powerful paradigm for automated algorithm design. However, existing LES methods primarily optimize for average performance, inherently directing search effort toward instances that contribute most to this metric while leaving others poorly served, resulting in weak tail robustness and limited real-world reliability. To address this limitation, we propose Dynamic Instance Clustering and Specialized Algorithm Design (DyCA), an LES framework with a feature-free, structure-aware mechanism for constructing reliable algorithm portfolios under heterogeneous instance distributions. DyCA treats instance clustering as a co-evolving component within the search process, reusing accumulated evaluation data as feature-free signals to progressively partition instances with similar algorithmic response patterns. The uncovered clusters decompose the mixed objective into a set of structure-aware sub-objectives, thereby enabling finer-grained and more adaptive guidance for specialized algorithm design. Experimental results across four algorithm design tasks with heterogeneous instances demonstrate that DyCA outperforms state-of-the-art LES baselines, improving tail robustness by an average of 15.2% and overall performance by 7.1% while maintaining competitive head performance.