Reasoning is a distinctive human capacity, enabling us to address complex problems by breaking them down into a series of manageable cognitive steps. Yet, complex logical reasoning is still cumbersome for language models. Based on the dual process theory in cognitive science, we are the first to unravel the cognitive reasoning abilities of language models. Our framework employs an iterative methodology to construct a Cognitive Tree (CogTree). The root node of this tree represents the initial query, while the leaf nodes consist of straightforward questions that can be answered directly. This construction involves two main components: the implicit extraction module (referred to as the intuitive system) and the explicit reasoning module (referred to as the reflective system). The intuitive system rapidly generates multiple responses by utilizing in-context examples, while the reflective system scores these responses using comparative learning. The scores guide the intuitive system in its subsequent generation step. Our experimental results on two popular and challenging reasoning tasks indicate that it is possible to achieve a performance level comparable to that of GPT-3.5 (with 175B parameters), using a significantly smaller language model that contains fewer parameters (<=7B) than 5% of GPT-3.5.

Cisco has unveiled what it's calling "intent-based networking solutions" which, it claims, are the culmination of its vision to create "an intuitive system that anticipates actions, stops security threats in their tracks, and continues to evolve and learn. It will help businesses to unlock new opportunities and solve previously unsolvable challenges in an era of increasing connectivity and distributed technology." Cisco's pitch is that companies are currently managing their networks through traditional IT processes that are not now sustainable as the network grows and gets more complex - there are just too many buttons to push and adjustments to be made, so the whole construction is becoming unmanageable, it claims. So in response Cisco's says it's harnessed the concept of'intent networking' to create an "intuitive system that uses AI and machine learning to constantly learn, adapt, automate and protect, to optimize network operations and defend against today's evolving threat landscape." The broad idea of an'intent model' is easy enough to understand and one of its most robust originators and promoters has been Tom Nolle of CIMI Research who, as I thought he might, has popped up today with a timely blog post on the Cisco launch.