ArenaFlow: From Trajectory Ranking to Hierarchical Credit Propagation for Open-Ended Agent RL
Reinforcement learning has substantially improved large language model (LLM) agents in verifiable domains, but remains difficult to apply to open-ended agent tasks, where solutions are diverse and reliable scalar rewards are hard to obtain. Recent pairwise evaluation methods alleviate reward discrimination collapse by...
Qiang Zhang, Rui-Xue Ding, Fanrui Zhang et al.
· 1 citation