DACMO constructs general-purpose parallel algorithm portfolios for multi-objective binary optimization via co-evolution of neural instance representations and LLM-generated operators, performing competitively on four problem classes without problem-specific generators.
LLM- driven instance-specific heuristic generation and selection
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
baseline 1
method 1
citation-polarity summary
years
2026 5verdicts
UNVERDICTED 5representative citing papers
AHD Agent trains a 4B-parameter LLM via agentic RL to actively use tools for automatic heuristic design, matching or exceeding larger baselines across eight domains with fewer evaluations.
IG-DOE combines stagnation-triggered operator switching with an LLM-evolved destruction operator ensemble to improve iterated greedy performance on large permutation flow shop scheduling instances.
MeEvo cyclically couples natural and metacognitive evolution in LLM-based automatic heuristic design to achieve stronger performance and lower variance on optimization problems.
TransGP uses a task-conditioned Transformer to guide genetic programming toward elite heuristics and generate task-specific rules for multitask dynamic flexible job shop scheduling, outperforming standard GP and handcrafted methods in experiments.
citing papers explorer
No citing papers match the current filters.