[2604.02226] When to ASK: Uncertainty-Gated Language Assistance for Reinforcement Learning

Computer Science > Artificial Intelligence arXiv:2604.02226 (cs) [Submitted on 2 Apr 2026] Title:When to ASK: Uncertainty-Gated Language Assistance for Reinforcement Learning Authors:Juarez Monteiro, Nathan Gavenski, Gianlucca Zuin, Adriano Veloso View a PDF of the paper titled When to ASK: Uncertainty-Gated Language Assistance for Reinforcement Learning, by Juarez Monteiro and 3 other authors View PDF HTML (experimental) Abstract:Reinforcement learning (RL) agents often struggle with out-of-distribution (OOD) scenarios, leading to high uncertainty and random behavior. While language models (LMs) contain valuable world knowledge, larger ones incur high computational costs, hindering real-time use, and exhibit limitations in autonomous planning. We introduce Adaptive Safety through Knowledge (ASK), which combines smaller LMs with trained RL policies to enhance OOD generalization without retraining. ASK employs Monte Carlo Dropout to assess uncertainty and queries the LM for action suggestions only when uncertainty exceeds a set threshold. This selective use preserves the efficiency of existing policies while leveraging the language model's reasoning in uncertain situations. In experiments on the FrozenLake environment, ASK shows no improvement in-domain, but demonstrates robust navigation in transfer tasks, achieving a reward of 0.95. Our findings indicate that effective neuro-symbolic integration requires careful orchestration rather than simple combination, highlighting t...