Graph-based Self-Adaptive Conversational Agent

In recent years, the topic of emotion reading has increasingly received attention from researchers in Cognitive Science and Artificial Intelligence. To study this phenomenon, in this paper an adaptive agent model is presented with capabilities to interpret another agent’s emotions. The presented agent model is based on recent advances in neurological context. First a non-adaptive agent model for emotion reading is described involving (preparatory) mirroring body states of the other agent. Here emotion reading is modelled taking into account the Simulation Theory perspective as known from the literature, involving the own body states and emotions in reading somebody else’s emotions. This models an agent that first develops the same feeling, and after feeling the emotion imputes it to the other agent. Next the agent model is extended to an adaptive model based on a Hebbian learning principle to develop a direct connection between a sensed stimulus concerning another agent’s body state (e.g., face expression) and the emotion recognition state. In this adaptive agent model the emotion is imputed to the other agent before it is actually felt. The agent model has been designed based on principles of neural modelling, and as such has a close relation to a neurological realisation.Keywordsagent modelemotion readingcognitivetheory of mindadaptive

Inspired by the work of Elaine Aron, in this paper a human-like adaptive computational agent model of the internal processes of a highly sensitive person (HSP) is presented. This agent model was used to get a better understanding of what goes wrong in these internal processes once this person gets upset. A scenario is addressed where a highly sensitive person will get upset by an external stimulus and will not be able to calm down by herself. Yet in a social context the interaction with a second person (without high sensitivity) will calm the HSP down, thus contributing to regulation. To obtain an adaptive model a Hebbian learning connection was integrated. During interaction with a second person this Hebbian learning link will become stronger, which makes it possible for a HSP to become independent after some time and be able to regulate upsetting external stimuli all by herself.

This paper describes an autonomous adaptive agent model of the UK market in electricity, where the agents represent electricity generating companies. We briefly describe the UK market in electricity generation, then detail the simplifications we have made. Our current model consists of a single adaptive agent bidding against several non-adaptive agents. The adaptive agent uses a hierarchical agent structure with two Learning Classifier Systems to evolve market bidding rules to meet two objectives. We detail how the agent interacts with its environment, the particular problems this environment presents to the agent and the agent and classifier architectures we used in our experiments. We present the results and conclude that using our structure can improve performance.

Maintenance accounts for a major cost of software development. The design of software systems from the very beginning phase to achieve adaptive behaviour should, therefore, be recognised of its importance in practice. Adaptive Agent Model (AAM) is aimed towards this end via using Agent-oriented Model-Driven Architecture. Models are derived from requirements and reconfigured continuously by domain experts to reflect changing business needs. Agents interpret these models, at runtime, to choose alternative partners in collaboration or reusable components in computation, in an adaptive manner. Adopting an event-driven architecture at runtime, AAM has its agents and knowledge-based control readily applicable to robots and their on-board control extension. The paper describes work towards this goal and ultimately, this will demonstrate the feasibility of AAM in software adaptivity via the robot platform, and also help to achieve robot adaptivity through corresponding AAM support.

Purpose Human–agent interaction (HAI) is increasingly influencing our personal and work lives through the proliferation of conversational agents (CAs) in various domains. As such, these agents combine intuitive natural language interactions by also delivering personalization through artificial intelligence capabilities. However, research on CAs as well as practical failures indicates that CA interaction oftentimes fails miserably. To reduce these failures, this paper introduces the concept of building common ground for more successful HAIs. Design/methodology/approach Based on a systematic literature analysis, we identified 38 articles meeting the eligibility criteria. We critically reviewed this body of knowledge within a formal narrative synthesis structured around the use of common ground in the interaction with CAs. Findings Based on the systematic review, our analysis reveals five mechanisms for achieving common ground: embodiment, social features, joint action, knowledge base and mental model of conversational agent. We point out the relationships between these mechanisms as they are related to each other in directional and bidirectional ways. Research limitations/implications Our findings contribute to theory with several implications for CA research. First, we provide implications about the organization of common ground mechanisms for CAs. Second, we provide insights into the mechanisms and nomological network for achieving common ground when interacting with CAs. Third, we provide a broad research agenda for future CA research that centers around the important topic of common ground for HAI. Originality/value We offer novel insights into grounding mechanisms and highlight the potentials when considering common ground in different HAI processes. Consequently, we secure further understanding and deeper insights of possible mechanisms of common ground to shape future HAI processes.

In this paper an adaptive agent model is presented that models how recurrent dreams such as nightmares occur. In the agent model recurring dreams emerge as scripts of connected dream episodes in which the connections between the episodes strengthen over time by Hebbian learning. The model was evaluated by a number of simulation experiments.

A special issue on ‘the emergence of language: neural and adaptive agent models’

The popularization and evolution of online conversational agents, also known as chatbots, provoked disruptive changes in the communication between institutions and people. Motivated by the growing need to provide more efficient mechanisms for information retrieval from legislation, manuals, and operational procedures, as well as taking advantage of recent technological developments, we propose an architectural model for conversational agents specialized in institutional information retrieval from unstructured documents (e.g., PDFs, DOCX). Besides, we present a conversational agent, created from our architectural model, to assist in the search and retrieve for information related to resolutions and internal regulations at our university. An evaluation performed with users using the System Usability Score (SUS) method revealed that our conversational agent presented itself as an effective alternative, achieving almost the best imaginable usability (SUS Score 89), and speeding up the search and retrieval for institutional information.

We investigate an evolution model of adaptive self-learning agents. The control system of agents is based on a neural network adaptive critic design. Each agent is a broker that predicts stock price changes and uses its predictions for action selection. We analyzed different regimes of learning and evolution and demonstrated that 1) evolution and learning together are more effective in searching for the optimal agent policy than evolution alone or learning alone; 2) in some regimes the Baldwin effect (genetic assimilation of initially acquired adaptive learning features during the course of Darwinian evolution) is observed; 3) inertial switching between two behavioral tactics similar to searching adaptive behavior of simple animals takes place during initial stages of evolutionary processes.KeywordsStock PriceAgent ResourceAdaptive AgentBaldwin EffectGenetic AssimilationThese keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Parents play an important role in the mental development of a child. In our previous work, we addressed how a narcissistic parent influences a child (online/offline) when (s)he is happy and admires the child. Now, we address the influence of a parent who is not so much pleased, and may curse the child for being the reason for his or her unhappiness. An abusive relationship with a parent can also cause trauma and poor mental health of the child. We also address how certain coping behaviors can help the child cope with such a situation. Therefore, the aim of the study is threefold. We present an adaptive agent model of a child, while incorporating the concept of mirroring through social contagion, the avoidance behaviors from a child, and the effects of regulation strategies to cope with stressful situations.

Pregnant women constantly need some information to support nutritional decisions during pregnancy, and many do not receive such assistance at all. This study aims to present a conversational agent to provide reliable information to pregnant women, focusing on nutritional education and evaluating the perception of pregnant women and health professionals about the agent. As a scientific contribution, this article developed and implemented a conversational agent in a real environment capable of generating reliable responses on the basis of a set of health documents. We proposed an intervention study with 25 women and 10 healthcare providers through a survey to measure the perceptions of these groups towards conversational agents. The results show that the intended design could ensure positive support for pregnant women, clarify certain issues for the public, and remove some knowledge barriers. The results showed no significant difference between the groups (p-value = 0.713). Depending on the perception of the pregnant group, the conversational agent model can teach new knowledge during the prenatal period (Mean = 4.56). The model presented for health professionals could already be indicated as a support tool for pregnant women (Mean = 4.7).

Design is a highly creative and challenging task and research has already explored possible ways for using conversational agents (CAs) to support humans participating in co-design sessions. However, research reports that a) humans in these sessions expect more essential support from CAs, and b) it is important to develop CAs that continually learn from communication -like humans do- and not simply from labeled datasets. Addressing the above needs, this paper explores the specific question of how to extract useful knowledge from human dialogues observed during co-design sessions and make this knowledge available through a CA supporting humans in similar design activities. In our approach we explore the potential of the GPT-3 Large Language Model (LLM) to provide useful output extracted from unstructured data such as free dialogues. We provide evidence that by implementing an appropriate “extraction task” on the LLM it is possible to efficiently (and without human-in-the-loop) extract knowledge that can then be embedded in the cognitive base of a CA. We identify at least four major steps/assumptions in this process that need to be further researched, namely: A1) Knowledge modeling, A2) Extraction task, A3) LLM-based facilitation, and A4) Humans’ benefit. We provide demonstrations of the extraction and facilitation steps using the GPT-3 model and we also identify and comment on various worth exploring open research questions.

Currently, there is a lack of tools to build autonomous software systems in a pervasive and distributed context. In this paper, we present a model and a development tool called Agentphi for building flexible agent architectures from fine-grained components. Reusable components implement non-functional mechanisms such as communication, mobility or adaptation skills. Each agent can dynamically and autonomously change its components to suit its runtime context, improving safety and performances of applications, particularly in open, pervasive or large-scale distributed applications. We also show how to use our agents to build applications from autonomous and adaptable systems.

Simulation-based models are becoming a promising research tool in financial markets. A general Complex Adaptive System can be tailored to different application scenarios. This paper describes an application of a Complex Adaptive System-based agent model in stock trades signalling. The model has been evaluated using historical movement of Bank of America stock. Agents in the system are initialized using random decision rules. Genetic algorithms and machine learning methods are utilized to reduce the sample space and improve the decision rules. Final rules are generated via Monte Carlo simulation and modified with a market momentum estimate. By following the advice suggested by the model. The hypothetical investors have outperformed the S&P 500 index and buy-and-hold investors. Compared with benchmark agents with buy-and-hold strategy on stock and index respectively, the model achieved higher return even in periods of stock’s poor performance. The stock trade-signalling model is implemented using the Netlogo framework.

Conversational agent technology is an emerging paradigm for creating a social environment in online groups that is conducive to effective teamwork. Prior work has demonstrated advantages in terms of learning gains and satisfaction scores when groups learning together online have been supported by conversational agents that employ Balesian social strategies. This prior work raises two important questions that are addressed in this article. The first question is one of generality. Specifically, are the positive effects of the designed support specific to learning contexts? Or are they in evidence in other collaborative task domains as well? We present a study conducted within a collaborative decision-making task where we see that the positive effects of the Balesian social strategies extend to this new context. The second question is whether it is possible to increase the effectiveness of the Balesian social strategies by increasing the context sensitivity with which the social strategies are triggered. To this end, we present technical work that increases the sensitivity of the triggering. Next, we present a user study that demonstrates an improvement in performance of the support agent with the new, more sensitive triggering policy over the baseline approach from prior work. The technical contribution of this article is that we extend prior work where such support agents were modeled using a composition of conversational behaviors integrated within an event-driven framework. Within the present approach, conversation is orchestrated through context-sensitive triggering of the composed behaviors. The core effort involved in applying this approach involves building a set of triggering policies that achieve this orchestration in a time-sensitive and coherent manner. In line with recent developments in data-driven approaches for building dialog systems, we present a novel technique for learning behavior-specific triggering policies, deploying it as part of our efforts to improve a socially capable conversational tutor agent that supports collaborative learning.