Search for: All records

Dialogue systems are designed to offer human users social support or functional services through natural language interactions. Traditional conversation research has put significant emphasis on a system’s response-ability, including its capacity to understand dialogue context and generate appropriate responses. However, the key element of proactive behavior—a crucial aspect of intelligent conversations—is often overlooked in these studies. Proactivity empowers conversational agents to lead conversations towards achieving pre-defined targets or fulfilling specific goals on the system side. Proactive dialogue systems are equipped with advanced techniques to handle complex tasks, requiring strategic and motivational interactions, thus representing a significant step towards artificial general intelligence. Motivated by the necessity and challenges of building proactive dialogue systems, we provide a comprehensive review of various prominent problems and advanced designs for implementing proactivity into different types of dialogue systems, including open-domain dialogues, task-oriented dialogues, and information-seeking dialogues. We also discuss real-world challenges that require further research attention to meet application needs in the future, such as proactivity in dialogue systems that are based on large language models, proactivity in hybrid dialogues, evaluation protocols and ethical considerations for proactive dialogue systems. By providing a quick access and overall picture of the proactive dialogue systems domain, we aim to inspire new research directions and stimulate further advancements towards achieving the next level of conversational AI capabilities, paving the way for more dynamic and intelligent interactions within various application domains. 

Abstract We study the universality of superconcentration for the free energy in the Sherrington–Kirkpatrick model. In [10], Chatterjee showed that when the system consists of spins and Gaussian disorders, the variance of this quantity is superconcentrated by establishing an upper bound of order , in contrast to the bound obtained from the Gaussian–Poincaré inequality. In this paper, we show that superconcentration indeed holds for any choice of centered disorders with finite third moment, where the upper bound is expressed in terms of an auxiliary nondecreasing function that arises in the representation of the disorder as for standard normal. Under an additional regularity assumption on , we further show that the variance is of order at most . 

We consider a restricted four-body problem, with a precise hierarchy between the bodies: two larger bodies and a smaller one, all three of oblate shape, and a fourth, infinitesimal body, in the neighborhood of the smaller of the three bodies. The three heavy bodies are assumed tomove in a plane under theirmutual gravity, and the fourth body to move in the three-dimensional space under the gravitational influence of the three heavy bodies, but without affecting them.We first find that the triangular central configuration of the three heavy oblate bodies is a scalene triangle (rather than an equilateral triangle as in the point mass case). Then, assuming that these three bodies are in such a central configuration, we perform a Hill approximation of the equations of motion describing the dynamics of the infinitesimal body in a neighborhood of the smaller body. Through the use of Hill’s variables and a limiting procedure, this approximation amounts to sending the two larger bodies to infinity. Finally, for the Hill approximation, we find the equilibrium points for the motion of the infinitesimal body and determine their stability. As a motivating example, we identify the three heavy bodies with the Sun, Jupiter, and the Jupiter’s Trojan asteroid Hektor, which are assumed to move in a triangular central configuration. Then, we consider the dynamics of Hektor’s moonlet Skamandrios.