Tag
The paper proposes active inference as a framework for AI agents to efficiently acquire context by balancing information gain and cost, with benchmarks on language models and applications in question asking and prompt optimization.
Ruby is a product that helps you ask better questions on every call, launched on Product Hunt.
Researchers at MIT CSAIL and Harvard used a modified Battleship game to study and improve language models' question-asking abilities. By applying Monte Carlo inference strategies, they significantly boosted smaller models like Llama 4 Scout's win rate from 8% to 82% against humans, outperforming larger models at a fraction of the cost.
Clarity Agent is an open-source AI tool from Microsoft that helps users clarify their thinking by asking questions, producing version-controlled Markdown documents for problem definition, solution analysis, and failure mode exploration.