On Information Self-Locking in Reinforcement Learning for Active Reasoning of LLM agents 事件

On Information Self-Locking in Reinforcement Learning for Active Reasoning of LLM agents arXiv:2603.12109v2 Announce Type: replace Abstract: Reinforcement learning (RL) has become a de facto paradigm for building LLM-based agents that act, interact, and reason over extended task horizons. However, in active reasoning where agents must elicit new observations through interaction with the environment to solve the task, we find that outcome-based RL can induce a systematic failure mode which we ca