Toward Generalized Web Agent Training: A Deep Dive into Entropy-Balanced Reinforcement Learning.

@inproceedings{dong-2026-toward, author = {Guanting Dong and Licheng Bao and Zhongyuan Wang and Kangzhi Zhao and Xiaoxi Li and Jiajie Jin and Jinghan Yang and Hangyu Mao and Fuzheng Zhang and Kun Gai and Guorui Zhou and Yutao Zhu and Ji-Rong Wen and Zhicheng Dou}, editor = {Hakim Hacid and Yoelle Maarek and Francesco Bonchi and Ido Guy and Emine Yilmaz}, title = {{Toward Generalized Web Agent Training: A Deep Dive into Entropy-Balanced Reinforcement Learning}}, booktitle = {{Proceedings of the ACM Web Conference 2026, WWW 2026, Dubai, United Arab Emirates, originally scheduled for April 13-17, 2026, rescheduled for June 29 - July 3, 2026}}, pages = {2126--2137}, publisher = {ACM}, year = {2026}, url = {https://doi.org/10.1145/3774904.3792301}, doi = {https://doi.org/10.1145/3774904.3792301} }