Cita APA (7a ed.)

Xu, T., Chen, Y., & Li, M. (2026). CLEANER: Self-Purified Trajectories Boost Agentic Reinforcement Learning.

Cita Chicago Style (17a ed.)

Xu, Tianshi, Yuteng Chen, y Meng Li. CLEANER: Self-Purified Trajectories Boost Agentic Reinforcement Learning. 2026.

Cita MLA (9a ed.)

Xu, Tianshi, et al. CLEANER: Self-Purified Trajectories Boost Agentic Reinforcement Learning. 2026.