Can Large Language Models Reason and Plan? Subbarao Kambhampati Large Language Models (LLMs), essentially n-gram models on steroids that have been trained on web-scale lan- guage corpora (or, effectively, our civilizational knowledge), have caught our collective imagination with linguis- tic behaviors that no one expected text completion systems to possess. By training and operation, LLMs are perhaps best seen as giant non-veridical memories akin to an external System 1 for us all (see Figure 1). Their seem- ing versatility has however led many researchers to wonder whether they can also do well on planning and reasoning tasks typically associated with System 2 competency. Nothing in the training and use of LLMs would seem to suggest remotely that they can do any type of princi- pled reasoning (which, as we know, often involves computationally hard inference/search). What LLMs are good at is a form of universal approximate retrieval. Unlike databases that index and retrieve data exactly, LLMs, as n- gram models, probabilistically reconstruct completions for the prompt word by word–a process we shall refer to as approximate retrieval. This means that LLMs can’t even guarantee memorizing complete answers, something that is the flip side of their appeal about constructing “novel” prompt completions on the fly. The boon (“creativity”) and bane (“hallucination”) of LLMs is that n-gram models will naturally mix and match–and have almost as much trouble strictly memorizing as we do. It is indeed the very basis of their appeal. https://nyaspubs.onlinelibrary.wiley.com/doi/10.1111/nyas.15125 oppure https://arxiv.org/pdf/2403.04121.pdf