Haoze Lv
2 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
The paper proposes PaW, a co-training framework that uses standard RL rollouts to provide auxiliary world model supervision directly during policy training, significantly improving language agent performance.
This paper proposes a new iterated greedy algorithm with a multi-operator approach and a large language model-assisted framework to enhance exploration and improve performance on the permutation flow shop scheduling problem.
Papers
Large Language Model-Driven Cooperative Operator Ensemble Evolution for Permutation Flow Shop Scheduling
Rui Xu, Yufan Liao, Haoze Lv, Shengcai Liu +2 more
This paper proposes a new iterated greedy algorithm with a multi-operator approach and a large language model-assisted framework to enhance exploration and improve performance on the permutation flow…