AI Paper Atlas

Research map / Learning theory and algorithms / Combinatorial and search optimization

Evolving Interdependent Operators with Large Language Models for Multi-Objective Combinatorial Optimization

junhao qiu, Xin Chen, Liang Ge, Liyong Lin, Zhichao Lu, Qingfu Zhang

ICML 2026 · Learning theory and algorithms › Combinatorial and search optimization · approach: Multi-objective optimization · 0 citations (OpenAlex)

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
evolve operator combinations with E2OC instead of expert operatorsNSGA-II · Bi-FJSPHV: 0.1996 -> 0.2435 (RI 22.00%)Improved
E2OC instead of expert operatorsNSGA-II · Bi-TSPHV: 0.3881 -> 0.4424 (RI 14.00%)Improved
E2OC instead of expert operatorsNSGA-II · Tri-FJSPHV: 0.1266 -> 0.1485 (RI 17.36%)Improved
E2OC instead of expert operatorsNSGA-II · Tri-TSPHV: 0.1824 -> 0.1939 (RI 6.30%)Improved
co-evolve design strategies versus sequentially optimizing single heuristicsE2OC vs MCTS-AHD · Bi-FJSPHV: 0.2269 -> 0.2435Improved
use direct LLM-guided operator combination controlmulti-heuristic co-design · Bi-FJSPHV: LLM 0.2148 vs Random 0.2263Hurt
replace progressive strategy search with fixed design strategy (ablation)E2OC (MCTS OC) · Bi-FJSPHV: 0.2435 -> 0.2085Hurt
add operator rotation instead of sequential operator design (ablation)E2OC · Bi-FJSPHV: 0.2187 -> 0.2435Improved
use EoH as underlying designer rather than ReEvo/FunSearch/MCTS-AHD (ablation)E2OC · Bi-FJSPHV: 0.2435 vs 0.2213 to 0.2269Improved
search a warm-start fixed design thought space instead of dynamic sampling (ablation)E2OC vs MCTS Sample · Bi-FJSPHV: 0.2181 -> 0.2435Improved
reuse E2OC outputs as inputs for further runs (ablation)E2OC · Bi-FJSPHV: 0.2435 -> 0.2454 -> 0.2475Improved
use stronger/more expensive LLM (gemini-2.5-pro) than deepseek-chat (ablation)E2OC · Bi-FJSPHV: 0.2271 vs 0.2223 HVNo clear effect

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