作者位次 #5/9ACL 2026Poster· Natural Language Processing
Breaking the Impasse: Dual-Scale Evolutionary Policy Training for Social Language Agents
Minzheng Wang · Run Luo · Yanbo Wang · Zichen Liu · Yuqiao Tan · Tao Tan · Nan Xu · Lu Wang · Wenji Mao
摘要
While Reinforcement Learning with Verifiable Rewards (RLVR) has proven effective for closed-ended tasks, extending it to open-ended social language games via self-play reveals a critical issue: evolution impasse. Due to the vast strategy space, language agents frequently converge to homogenized b...