In this work, we propose a novel framework that integrates large language models (LLMs) with an RL-based dialogue manager for open-ended dialogue with a specific goal. By leveraging hierarchical reinforcement learning to model the structured phases of dialogue and employ meta-learning to enhance adaptability across diverse user profiles, our approach enhances adaptability and efficiency, enabling the system to learn from limited data, transition fluidly between dialogue phases, and personalize responses to heterogeneous patient needs. We apply our framework to Motivational Interviews, aiming to foster behavior change, and demonstrate that the proposed dialogue manager outperforms a state-of-the-art LLM baseline in terms of reward, showing a potential benefit of conditioning LLMs to create open-ended dialogue systems with specific goals.

Current Conversational AI systems employ different machine learning pipelines, as well as external knowledge sources and business logic to predict the next action. Maintaining various components in dialogue managers' pipeline adds complexity in expansion and updates, increases processing time, and causes additive noise through the pipeline that can lead to incorrect next action prediction. This paper investigates graph integration into language transformers to improve understanding the relationships between humans' utterances, previous, and next actions without the dependency on external sources or components. Experimental analyses on real calls indicate that the proposed Graph Integrated Language Transformer models can achieve higher performance compared to other production level conversational AI systems in driving interactive calls with human users in real-world settings.

Social robots are robots that are designed specifically to interact with their human users [14] for example by using spoken dialogue. For social robots, the interaction with humans plays a crucial role [7, 27], for example in the context of elderly care [15] or education [9]. Robots that use speech as a main mode of interaction do not only need to understand the user's utterances, but also need to select appropriate responses given the context. Dialogue management (DM), according to Traum and Larsson [88], is the part of a dialogue system that performs four key functions: 1) it maintains and updates the context of the dialogue, 2) it includes the context of the utterance for interpretation of input, 3) it selects the timing and content of the next utterance, and 4) it coordinates with (non-)dialogue modules. In spoken dialogue systems, the dialogue manager receives its input from a natural language understanding (NLU) module and forwards its results to a natural language generation (NLG) module, which then generates the output (see Figure 1). In contrast to general DM, DM in human-robot interaction (HRI) has to also consider and manage the complexity added by social robots (see Figure 1). The concentric circles of the figure describe decisions that have to be made when designing a dialogue manager for human-robot interaction. From each circle, one or more options can be chosen and combined with each other.

Dialogue-based human-AI collaboration can revolutionize collaborative problem-solving, creative exploration, and social support. To realize this goal, the development of automated agents proficient in skills such as negotiating, following instructions, establishing common ground, and progressing shared tasks is essential. This survey begins by reviewing the evolution of dialogue management paradigms in collaborative dialogue systems, from traditional handcrafted and information-state based methods to AI planning-inspired approaches. It then shifts focus to contemporary data-driven dialogue management techniques, which seek to transfer deep learning successes from form-filling and open-domain settings to collaborative contexts. The paper proceeds to analyze a selected set of recent works that apply neural approaches to collaborative dialogue management, spotlighting prevailing trends in the field. This survey hopes to provide foundational background for future advancements in collaborative dialogue management, particularly as the dialogue systems community continues to embrace the potential of large language models.

Task-oriented dialogue systems are designed to achieve specific goals while conversing with humans. In practice, they may have to handle simultaneously several domains and tasks. The dialogue manager must therefore be able to take into account domain changes and plan over different domains/tasks in order to deal with multidomain dialogues. However, learning with reinforcement in such context becomes difficult because the state-action dimension is larger while the reward signal remains scarce. Our experimental results suggest that structured policies based on graph neural networks combined with different degrees of imitation learning can effectively handle multi-domain dialogues. The reported experiments underline the benefit of structured policies over standard policies.

The conversational agents is one of the most interested topics in computer science field in the recent decade. Which can be composite from more than one subject in this field, which you need to apply Natural Language Processing Concepts and some Artificial Intelligence Techniques such as Deep Learning methods to make decision about how should be the response. This paper is dedicated to discuss the system architecture for the conversational agent and explain each component in details.

We present a new approach to dialogue specification for Virtual Personal Assistants (VPAs) based on so-called dialogue workflow graphs, with several demonstrated advantages over current ontology-based methods. Our new dialogue specification language (DSL) enables customers to more easily participate in the VPA modeling process due to a user-friendly modeling framework. Resulting models are also significantly more compact. VPAs can be developed much more rapidly. The DSL is a new modeling layer on top of our ontology-based Dialogue Management (DM) framework OntoVPA. We explain the rationale and benefits behind the new language and support our claims with concrete reduced Level-of-Effort (LOE) numbers from two recent OntoVPA projects.

We propose a framework to integrate the concept of Theory of Mind (ToM) into generating utterances for task-oriented dialogue. Our approach explores the ability to model and infer personality types of opponents, predicts their responses, and uses this information to adapt the agent's high-level strategy in negotiation tasks. We introduce a probabilistic formulation for the first-order theory of mind and test our approach on the CraigslistBargain dataset. Experiments show that our method using ToM inference achieves a 40\% higher dialogue agreement rate compared to baselines on a mixed population of opponents. We also show that our model displays diverse negotiation behavior with different types of opponents.

Inspired by studies on the overwhelming presence of experience-sharing in human-human conversations, Emora, the social chatbot developed by Emory University, aims to bring such experience-focused interaction to the current field of conversational AI. The traditional approach of information-sharing topic handlers is balanced with a focus on opinion-oriented exchanges that Emora delivers, and new conversational abilities are developed that support dialogues that consist of a collaborative understanding and learning process of the partner's life experiences. We present a curated dialogue system that leverages highly expressive natural language templates, powerful intent classification, and ontology resources to provide an engaging and interesting conversational experience to every user.

Considerable progress has been made towards conversational models that generate coherent and fluent responses by training large language models on large dialogue datasets. These models have little or no control of the generated responses and miss two important features: continuous dialogue skills integration and seamlessly leveraging diverse knowledge sources. In this paper, we propose the Adapter-Bot, a dialogue model that uses a fixed backbone conversational model such as DialGPT (Zhang et al., 2019) and triggers on-demand dialogue skills (e.g., emphatic response, weather information, movie recommendation) via different adapters (Houlsby et al., 2019). Each adapter can be trained independently, thus allowing a continual integration of skills without retraining the entire model. Depending on the skills, the model is able to process multiple knowledge types, such as text, tables, and graphs, in a seamless manner. The dialogue skills can be triggered automatically via a dialogue manager, or manually, thus allowing high-level control of the generated responses. At the current stage, we have implemented 12 response styles (e.g., positive, negative etc.), 8 goal-oriented skills (e.g. weather information, movie recommendation, etc.), and personalized and emphatic responses. We evaluate our model using automatic evaluation by comparing it with existing state-of-the-art conversational models, and we have released an interactive system at adapter.bot.ust.hk.