Compute Allocation in Evolutionary Search: From Depth-Breadth to Multi-Armed Bandits

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Xing, Sixue, He, Haoyu, Wu, Kerui, Yang, Zhuo, Luo, Haozheng, Fu, Tianfan, Nagarajan, Aarthy
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866911730680987648
author Xing, Sixue
He, Haoyu
Wu, Kerui
Yang, Zhuo
Luo, Haozheng
Fu, Tianfan
Nagarajan, Aarthy
author_facet Xing, Sixue
He, Haoyu
Wu, Kerui
Yang, Zhuo
Luo, Haozheng
Fu, Tianfan
Nagarajan, Aarthy
contents LLM-guided evolutionary search (Evolve systems) has reached state-of-the-art results on mathematical and combinatorial tasks, yet most existing systems report only the best of many runs and leave the run-to-run distribution undocumented. We ask how a fixed budget of LLM calls should be allocated, and how reliably a single run reaches the reported numbers. Sweeping the depth-breadth grid over five models and three tasks, we identify two empirical regularities: a fitness-compute envelope along which capability ordering largely collapses on effective FLOPs, and a bilinear depth-breadth fit with task-specific interaction; both are gated by model-task capability. Motivated by these regularities, we propose BaSE (Bandit-based Self-Evolving), a multi-armed bandit that allocates LLM calls across parallel trajectories. Without changing the model, prompt, or evaluator, BaSE improves mean fitness by 12.3% over the strongest island-protocol baseline across 8 (model, task) cells, with the largest gains on high-variance settings: a reliability gain from allocation alone.
format Preprint
id arxiv_https___arxiv_org_abs_2605_29268
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Compute Allocation in Evolutionary Search: From Depth-Breadth to Multi-Armed Bandits
Xing, Sixue
He, Haoyu
Wu, Kerui
Yang, Zhuo
Luo, Haozheng
Fu, Tianfan
Nagarajan, Aarthy
Computation and Language
Artificial Intelligence
Machine Learning
Neural and Evolutionary Computing
LLM-guided evolutionary search (Evolve systems) has reached state-of-the-art results on mathematical and combinatorial tasks, yet most existing systems report only the best of many runs and leave the run-to-run distribution undocumented. We ask how a fixed budget of LLM calls should be allocated, and how reliably a single run reaches the reported numbers. Sweeping the depth-breadth grid over five models and three tasks, we identify two empirical regularities: a fitness-compute envelope along which capability ordering largely collapses on effective FLOPs, and a bilinear depth-breadth fit with task-specific interaction; both are gated by model-task capability. Motivated by these regularities, we propose BaSE (Bandit-based Self-Evolving), a multi-armed bandit that allocates LLM calls across parallel trajectories. Without changing the model, prompt, or evaluator, BaSE improves mean fitness by 12.3% over the strongest island-protocol baseline across 8 (model, task) cells, with the largest gains on high-variance settings: a reliability gain from allocation alone.
title Compute Allocation in Evolutionary Search: From Depth-Breadth to Multi-Armed Bandits
topic Computation and Language
Artificial Intelligence
Machine Learning
Neural and Evolutionary Computing
url https://arxiv.org/abs/2605.29268