Amazon (auto-discovered)

Researchers at Amazon have developed a method to train large language models to generate multiple, diverse reasoning paths for the same problem, improving their decision-making accuracy. The team intr…

Amazon researchers have developed a new scaling law that connects large language model architecture directly to inference efficiency, enabling faster text generation without sacrificing accuracy. The …

Promptimus, a new method for automatically optimizing well-developed large language model prompts, eliminates the need for manual engineering by using AI agents to identify failure points and surgical…