Algorithm of Thoughts: Enhancing Exploration of Ideas in Large Language Models Figure 2: Illustration outlining various strategies for tackling reasoning problems with LLMs. Each box signifies a distinct thought, functioning as a unified string of words that forms an incremental pathway to reasoning. Green boxes indicate ideas deemed promising by the LLM, while red boxes represent less promising concepts.
https://files.mastodon.social/media_attachments/files/110/939/634/382/682/304/original/e8bd677642b61669.png