@article{beyondhumanpreferencesexploring, title = {Beyond Human Preferences: Exploring Reinforcement Learning Trajectory Evaluation and Improvement through LLMs}, author = {Zichao Shen and Tianchen Zhu and Qingyun Sun and Shiqi Gao and JianXin Li}, year = {2024}, eprint = {2406.19644}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2406.19644v2}, }