Closing the Feedback Loop: From Experience Extraction to Insight Governance in Verbal Reinforcement Learning

@misc{cui2026closing,
  title = {Closing the Feedback Loop: From Experience Extraction to Insight Governance in Verbal Reinforcement Learning},
  author = {Yanwei Cui and Xing Zhang and Yulong Zhang and Li Shao and Xiaofeng Shi and Guanghui Wang and Peiyang He},
  year = {2026},
  eprint = {2606.17591},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2606.17591},
}