“To summarize, nothing that I have read, verified or done gives me any compelling reason to believe that LLMs do reasoning/planning as it is normally understood. What they do, armed with their web-scale training, is a form of universal approximate retrieval which, as we have argued, can sometimes be mistaken for reasoning capabilities. LLMs do excel in idea generation for any task – including those involving reasoning, and as I pointed out, this can be effectively leveraged to support reasoning/planning. In other words, LLMs already have enough amazing approximate retrieval abilities that we can gainfully leverage, that we don’t need to ascribe fake reasoning/planning capabilities to them.”
– Subbarao Kambhampati (2023, Sept 12). Can LLMs Really Reason and Plan? blog@CACM, Communications of the ACM.