@article{reinforcingquestionansweringagentswith, title = {Reinforcing Question Answering Agents with Minimalist Policy Gradient Optimization}, author = {Yihong Wu and Liheng Ma and Muzhi Li and Jiaming Zhou and Jianye Hao and Ho-fung Leung and Irwin King and Yingxue Zhang and Jian-Yun Nie}, year = {2025}, eprint = {2505.17086}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2505.17086v1}, }