Yuhan Chen 0001, Yuxuan Liu 0009, Long Zhang, Pengzhi Gao, Jian Luan 0001, Wei Liu 0302. STEP: Success-Rate-Aware Trajectory-Efficient Policy Optimization. In Maria Liakata, Viviane P. Moreira, Jiajun Zhang 0001, David Jurgens, editors, Findings of the Association for Computational Linguistics, ACL 2026, San Diego, California, United States, July 2-7, 2026. pages 30681-30692, Association for Computational Linguistics, 2026. [doi]
Abstract is missing.