OOM-RL论文：以资金耗尽约束对齐多智能体系统

1. 12:00
   arXiv · Software Engineering

   OOM-RL：面向基于 LLM 的多智能体系统的资金耗尽强化学习市场驱动对齐

   论文提出 OOM-RL（Out-of-Money Reinforcement Learning）对齐范式，将智能体投入真实金融市场，以资金耗尽作为外部施加的负梯度，替代 RLHF / RLAIF 中易引发模型谄媚的内部评估。

Current heat 9·Comparable peak 10（Oct 8）·Comparable change over 24 hours –

The trend compares only the same participants observed continuously; its range may be smaller than the current heat count. Move or click on the chart to inspect hourly heat; use the left and right arrow keys to switch.