Tag
A tweet highlights the cognitive dissonance between writers who benefit from AI writing assistance and readers who perceive it negatively, citing a survey that shows readers avoid authors suspected of using AI.
This paper proposes ASK+, a method for uncertainty-gated assistance from small language models (SLMs) to reinforcement learning agents in partially observable environments (POMDPs). By providing trajectory-aware context and structured chain-of-thought reasoning, ASK+ significantly improves success rates over baselines, demonstrating that prompt design and selective gating dominate model scale.