AI Paper Atlas

Research map / Large language models / Agents, code and math

AutoEP: LLMs-Driven Automation of Hyperparameter Evolution for Metaheuristic Algorithms

Zhenxing Xu, Yizhe Zhang, Weidong Bao, Hao Wang, Ming Chen, Haoran Ye, Wenzheng Jiang, Hui Yan, Ji Wang

ICLR 2026 · Large language models › Agents, code and math · approach: LLMs for optimization and heuristics

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add ELA features to the LLM input (ablation)AutoEP on GA-2opt · TSPLIB dsj1000optimality gap (%): 6.46 -> 3.58Improved
use the multi-LLM Chain of Reasoning instead of a single LLM (ablation)AutoEP on GA-2opt · TSPLIB dsj1000optimality gap (%): 7.11 -> 3.58Improved
include ELA and CoR together versus neither (ablation)AutoEP on GA-2opt · TSPLIB dsj1000optimality gap (%): 7.93 -> 3.58Improved
replace Qwen3-30B CoR with a single large proprietary reasoning LLM (GPT-o1) (ablation)AutoEP · TSPLIB eil51runtime (min): 5.8 -> 44.7Hurt
replace Qwen3-30B CoR with single GPT-o1 (ablation)AutoEP · TSPLIB dsj1000optimality gap (%): 1.58 -> 1.59No clear effect
limit experience pool to sliding window of 20 iterations instead of full history (ablation)AutoEP on GA-2opt · TSP-100optimality gap (%): 0.17 -> 0.01Improved
shrink experience window from 20 to 5 (ablation)AutoEP on GA-2opt · TSP-100optimality gap (%): 0.01 -> 0.04Hurt
enlarge experience window from 20 to 50 (ablation)AutoEP on GA-2opt · TSP-100optimality gap (%): 0.01 -> 0.03Hurt
adjust hyperparameters every 3-5 iterations instead of every iteration (ablation)AutoEP · UAV-300convergence speedMixed
add AutoEP to GA-2optGA-2opt · TSPLIB dsj1000optimality gap (%): 7.14 -> 3.58Improved
add AutoEP on top of EoH or ReEvo enhanced GA-2optGA-2opt+EoH, GA-2opt+ReEvo · TSPLIB dsj1000optimality gap (%): 5.83 -> 3.61 (EoH)Improved
use smaller open LLMs in AutoEP versus EoH and ReEvoAutoEP · GA-2opt, various LLMsoptimality gapImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy