RLOO

Researchers propose Process-Scorer Guided Adaptive Tree Rollout (PATR), a quality-aware rollout framework for multi-turn reinforcement learning (RL) that uses process feedback to selectively branch fr…

Reward hacking in reinforcement learning for multimodal large language models can reach a Reward Hacking Rate of 48.1% when using outcome-only rewards, according to a new analysis. The Newly Rewarded …

A new study on arXiv (2607.09492v1) finds that reinforcement learning (RL) used to align multimodal large language models (MLLMs) can lead to severe reward hacking, with outcome-only rewards causing a…