Lang Feng 0002 Jiahao Lin Dong Xing Li Zhang 0045 De Ma Gang Pan 0001 Bidirectional Distillation: A Mixed-Play Framework for Multi-Agent Generalizable Behaviors. 2025 May abs/2505.11100 CoRR https://doi.org/10.48550/arXiv.2505.11100 db/journals/corr/corr2505.html#abs-2505-11100 streams/journals/corr