Humans possess innate collaborative capacities. However, effective teamwork often remains challenging. This study delves into the feasibility of collaboration within teams of rational, selfinterested agents who engage in teamwork without the obligation to contribute. Drawing from psychological and game theoretical frameworks, we formalise teamwork as a one-shot aggregative game, integrating insights from Steiner’s theory of group productivity. We characterise this novel game’s Nash equilibria and propose a multiagent multi-armed bandit system that learns to converge to approximations of such equilibria. Our research contributes value to the areas of game theory and multiagent systems, paving the way for a better understanding of voluntary collaborative dynamics. We examine how team heterogeneity, task typology, and assessment difficulty inuence agents’ strategies and resulting teamwork outcomes. Finally, we empirically study the behaviour of work teams under incentive systems that defy analytical treatment. Our agents demonstrate human-like behaviour patterns, corroborating ndings from social psychology research.

Humans possess innate collaborative capacities. However, effective teamwork often remains challenging. This study delves into the feasibility of collaboration within teams of rational, self-interested agents who engage in teamwork without the obligation to contribute. Drawing from psychological and game theoretical frameworks, we formalise teamwork as a one-shot aggregative game, integrating insights from Steiner's theory of group productivity. We characterise this novel game's Nash equilibria and propose a multiagent multi-armed bandit system that learns to converge to approximations of such equilibria. Our research contributes value to the areas of game theory and multiagent systems, paving the way for a better understanding of voluntary collaborative dynamics. We examine how team heterogeneity, task typology, and assessment difficulty influence agents' strategies and resulting teamwork outcomes. Finally, we empirically study the behaviour of work teams under incentive systems that defy analytical treatment. Our agents demonstrate human-like behaviour patterns, corroborating findings from social psychology research.

Recent advanced AI technologies, especially large language models (LLMs) like GPTs, have significantly advanced the field of data mining and led to the development of various LLM-based applications. AI for education (AI4EDU) is a vibrant multi-disciplinary field of data mining, machine learning, and education, with increasing importance and extraordinary potential. In this field, LLM and adaptive learning-based models can be utilized as interfaces in human-in-the-loop education systems, where the model serves as a mediator among the teacher, students, and machine capabilities, including its own. This perspective has several benefits, including the ability to personalize interactions, allow unprecedented flexibility and adaptivity for human-AI collaboration and improve the user experience. However, several challenges still exist, including the need for more robust and efficient algorithms, designing effective user interfaces, and ensuring ethical considerations are addressed. This workshop aims to bring together researchers and practitioners from academia and industry to explore cutting-edge AI technologies for personalized education, especially the potential of LLMs and adaptive learning technologies.

Ostrom's Institutional Analysis and Development (IAD) framework represents a comprehensive theoretical effort to identify and outline the variables that determine the outcome in any social interaction. Taking inspiration from it, we define the Action Situation Language (ASL), a machine-readable logical language to express the components of a multiagent interaction, with a special focus on the rules adopted by the community. The ASL is complemented by a game engine that takes an interaction description as input and automatically grounds its semantics as an Extensive-Form Game (EFG), which can be readily analysed using standard game-theoretical solution concepts. Overall, our model allows a community of agents to perform what-if analysis on a set of rules being considered for adoption, by automatically connecting rule configurations to the outcomes they incentivize.

Abstract This paper presents a novel model, called TomAbd, that endows autonomous agents with Theory of Mind capabilities. TomAbd agents are able to simulate the perspective of the world that their peers have and reason from their perspective. Furthermore, TomAbd agents can reason from the perspective of others down to an arbitrary level of recursion, using Theory of Mind of $$n^{\text {th}}$$ n th order. By combining the previous capability with abductive reasoning, TomAbd agents can infer the beliefs that others were relying upon to select their actions, hence putting them in a more informed position when it comes to their own decision-making. We have tested the TomAbd model in the challenging domain of Hanabi, a game characterised by cooperation and imperfect information. Our results show that the abilities granted by the TomAbd model boost the performance of the team along a variety of metrics, including final score, efficiency of communication, and uncertainty reduction.

Abstract The School-Work Alternation (SWA) programme was developed (under a European Commission call) to bridge the gaps and establish a well-tuned partnership between education and the job market. This work details the development of the AI4Citizen pilot, an AI software suite designed to support the SWA programme. The AI4Citizen pilot, developed within the H2020 AI4EU project, offers AI tools to automate and enhance the current SWA process. At the same time, the AI4Citizen pilot offers novel tools to support the complex problem of allocating student teams to internship programs, promoting collaborative learning and teamwork skills acquisition. Notably, the AI4Citizen pilot corresponds to a pipeline of AI tools, integrating existing and novel technologies. Our exhaustive empirical analysis confirms that the AI4Citizen pilot can alleviate the difficulties of current processes in the SWA, and therefore it is ready for real-world deployment.

Policies that seek to mitigate poverty by acting on equal opportunity have been found to aggravate discrimination against the poor (aporophobia), since individuals are made responsible for not progressing in the social hierarchy. Only a minority of the poor benefit from meritocracy in this era of growing inequality, generating resentment among those who seek to escape their needy situations by trying to climb up the ladder. Through the formulation and development of an agent-based social simulation, this study aims to analyse the role of norms implementing equal opportunity and social solidarity principles as enhancers or mitigators of aporophobia, as well as the threshold of aporophobia that would facilitate the success of poverty-reduction policies. The ultimate goal of the social simulation is to extract insights that could help inform and guide a new generation of policy making for poverty reduction by acting on the discrimination against the poor, in line with the UN “Leave No One Behind” principle. An “aporophobia-meter” will be developed and guidelines will be drafted based on both the simulation results and a review of poverty reduction policies at regional levels.

The Institutional Analysis and Development (IAD) framework developed by Elinor Ostrom and colleagues provides great conceptual clarity on the immensely varied topic of social interactions. In this work, we propose a computational model to examine the impact that any of the variables outlined in the IAD framework has on the resulting social interactions. Of particular interest are the rules adopted by a community of agents, as they are the variables most susceptible to change in the short term. To provide systematic descriptions of social interactions, we define the Action Situation Language (ASL) and provide a game engine capable of automatically generating formal game-theoretical models out of ASL descriptions. Then, by incorporating any agent decision-making models, the connection from a rule configuration description to the outcomes encouraged by it is complete. Overall, our model enables any community of agents to perform what-if analysis, where they can foresee and examine the impact that a set of regulations will have on the social interaction they are engaging in. Hence, they can decide whether their implementation is desirable.

The value alignment problem is concerned with the design of systems that provably abide by our human values. One approach to this challenge is through the leverage of prescriptive norms that, if carefully designed, are able to steer a multiagent system away from harmful outcomes and towards more beneficial ones. In this work, we first present a general methodology for the automated synthesis of value aligned normative systems, based on a consequentialist view of values. In the second part, we provide analytical tools to examine such value aligned normative systems, namely the Shapley value of individual norms and the compatibility of several values under a fixed set of norms. We illustrate all of our contributions with a running example of a society of agents where taxes are collected and redistributed according to a set of parametrised norms.

In education, student teams are composed aiming at completing academic tasks and co-learning. Key factors influencing team performance are individual competencies, personality and gender. In this paper, we present a computational model to compose proficient and congenial teams based on students' personalities, gender, and competencies to perform tasks of different nature. Our model, called synergistic team composition, extends Wilde's post-Jungian method, which solely employs individuals' personalities and gender. In addition to formally present the synergistic team composition problem, we develop an approximate algorithm to solve it. That is, an algorithm that partitions student groups into teams that are diverse in competencies, personality and gender. Finally, we discuss our positive empirical results on student performance.

The Belief-Desire-Intention (BDI) architecture is a practical approach for modelling large-scale intelligent systems. In the BDI setting, a complex system is represented as a network of interacting agents - or components - each one modelled based on its beliefs, desires and intentions. However, current BDI implementations are not well-suited for modelling more realistic intelligent systems which operate in environments pervaded by different types of uncertainty. Furthermore, existing approaches for dealing with uncertainty typically do not offer syntactical or tractable ways of reasoning about uncertainty. This complicates their integration with BDI implementations, which heavily rely on fast and reactive decisions. In this paper, we advance the state-of-the-art w.r.t. handling different types of uncertainty in BDI agents. The contributions of this paper are, first, a new way of modelling the beliefs of an agent as a set of epistemic states. Each epistemic state can use a distinct underlying uncertainty theory and revision strategy, and commensurability between epistemic states is achieved through a stratification approach. Second, we present a novel syntactic approach to revising beliefs given unreliable input. We prove that this syntactic approach agrees with the semantic definition, and we identify expressive fragments that are particularly useful for resource-bounded agents. Third, we introduce full operational semantics that extend CAN, a popular semantics for BDI, to establish how reasoning about uncertainty can be tightly integrated into the BDI framework. Fourth, we provide comprehensive experimental results to highlight the usefulness and feasibility of our approach, and explain how the generic epistemic state can be instantiated into various representations.

This paper proposes a computational model based on peer reviews for assessing the reputation of researchers and research work. We argue that by relying on peer opinions, we address some of the pitfalls of current approaches for calculating the reputation of authors and papers. We also introduce a much needed feature for review management: calculating the reputation of reviews and reviewers.

We propose a novel trust model for assessing the trustworthiness of advice. We say an advice is composed of a plan to execute and a goal to be fulfilled. The expectation of an advice's outcome is calculated by assessing the probabilities of commiting to and executing the plan, and the probability of the executed plan fulfiling the intended goal. The probabilities are learned from similar past experiences.

Revising its beliefs when receiving new information is an important ability of any intelligent system. However, in realistic settings the new input is not always certain. A compelling way of dealing with uncertain input in an agent-based setting is to treat it as unreliable input, which may strengthen or weaken the beliefs of the agent. Recent work focused on the postulates associated with this form of belief change and on finding semantical operators that satisfy these postulates. In this paper we propose a new syntactic approach for this form of belief change and show that it agrees with the semantical definition. This makes it feasible to develop complex agent systems capable of efficiently dealing with unreliable input in a semantically meaningful way. Additionally, we show that imposing restrictions on the input and the beliefs that are entailed allows us to devise a tractable approach suitable for resource-bounded agents or agents where reactive ness is of paramount importance.

When an agent wants to fulfill its desires about the world, the agent usually has multiple plans to choose from and these plans have different pre-conditions and additional effects in addition to achieving its goals. Therefore, for further reasoning and interaction with the world, a plan selection strategy (usually based on plan cost estimation) is mandatory for an autonomous agent. This demand becomes even more critical when uncertainty on the observation of the world is taken into account, since in this case, we consider not only the costs of different plans, but also their chances of success estimated according to the agent's beliefs. In addition, when multiple goals are considered together, different plans achieving the goals can be conflicting on their preconditions (contexts) or the required resources. Hence a plan selection strategy should be able to choose a subset of plans that fulfills the maximum number of goals while maintaining context consistency and resource-tolerance among the chosen plans. To address the above two issues, in this paper we first propose several principles that a plan selection strategy should satisfy, and then we present selection strategies that stem from the principles, depending on whether a plan cost is taken into account. In addition, we also show that our selection strategy can partially recover intention revision.

This paper proposes the notion of experience to help situate agents in their environment, providing a link on how the continually evolving environment impacts the evolution of an agent's BDI model and vice versa. Then, using the notion of shared experience as a primitive construct, we develop a novel formal model of shared intention which we believe more adequately describes social behaviour than traditional BDI logics that focus on individual agents. Whilst many philosophers have argued that collective intentionality cannot always be equated to the collection of the individual agents' intentions, there has been no AI model that addresses this issue. We believe this is the first attempt to develop an explicit notion of shared experience from an AI perspective.

This article addresses the problem of finding suitable agents to collaborate with for a given interaction in distributed open systems, such as multiagent and P2P systems. The agent in question is given the chance to describe its confidence in its own capabilities. However, since agents may be malicious, misinformed, suffer from miscommunication, and so on, one also needs to calculate how much trusted is that agent. This article proposes a novel trust model that calculates the expectation about an agent's future performance in a given context by assessing both the agent's willingness and capability through the semantic comparison of the current context in question with the agent's performance in past similar experiences. The proposed mechanism for assessing trust may be applied to any real world application where past commitments are recorded and observations are made that assess these commitments, and the model can then calculate one's trust in another with respect to a future commitment by assessing the other's past performance.

Just as conventional institutions are organisational structures for coordinating the activities of multiple interacting individuals, electronic institutions provide a computational analogue for coordinating the activities of multiple interacting software agents. In this paper, we argue that open multi-agent systems can be effectively designed and implemented as electronic institutions, for which we provide a comprehensive computational model. More specifically, the paper provides an operational semantics for electronic institutions, specifying the essential data structures, the state representation and the key operations necessary to implement them. We specify the agent workflow structure that is the core component of such electronic institutions and particular instantiations of knowledge representation languages that support the institutional model. In so doing, we provide the first formal account of the electronic institution concept in a rigorous and unambiguous way.

Trust and reputation measures are crucial in distributed open systems where agents need to decide whom or what to choose. Existing work has overlooked the impact of an entity's position in its structural graph and its effect on the propagation of trust in such graphs. This paper presents an algorithm for the propagation of reputation in structural graphs. It allows agents to infer their opinion about unfamiliar entities based on their view of related entities. The proposed mechanism focuses on the “part of” relation to illustrate how reputation may flow (or propagate) from one entity to another. The paper bases its reputation measures on opinions, which it defines as probability distributions over an evaluation space, providing a rich representation of opinions.

Our research combines electronic institutions and 3D virtual worlds for the construction of virtual institutions which are virtual worlds with normative regulation of interactions. That is, a virtual world where participants actions have to comply with predefined institutional rules. In this context, the actions a participant may perform depend on the institutional rules and the current execution state. We propose to include iObjects, intelligent objects, as entities having both visualization properties and decision mechanisms in the virtual institution. They are a new key element to improve users participation in virtual institutions. We situate them in a middleware infrastructure in order to be independent of 3D virtual world platform and to provide a general solution in which participants could be connected from different immersive environment platforms.

In this article, we build upon a multiagent architecture for landmark-based navigation in unknown environments. In this architecture, each of the agents in the navigation system has a bidding function that is controlled by a set of parameters. We show here the good results obtained by an evolutionary approach that tunes the parameter set values for two navigation tasks. © 2005 Wiley Periodicals, Inc. Int J Int Syst 20: 523–539, 2005.

Engineering individual components of a multi-agent system and their interactions is a complex and error-prone task in urgent need of methods and tools. Prototyping is a valuable technique to help software engineers explore the design space while gaining insight and a "feel" for the dynamics of the system; prototyping also allows engineers to learn more about the relationships among design features and the desired computational behaviour. In this paper we describe an approach to building prototypes of large multi-agent systems with which we can experiment and analyse results. We have implemented an environment embodying our approach. This environment is supported by a distributed platform that helps us achieve controlled simulations.

In the area of agent‐based computing there are many proposals for specific system architectures, and a number of proposals for general approaches to building agents. As yet, however, there are comparatively few attempts to relate these together, and even fewer attempts to provide methodologies which relate designs to architectures and then to executable agents. This paper provides a first attempt to address this shortcoming. We propose a general method of specifying logic‐based agents, which is based on the use of multi‐context systems, and give examples of its use. The resulting specifications can be directly executed, and we discuss an implementation which makes this direct execution possible.

The need for negotiation in multi-agent systems stems from the requirement for agents to solve the problems posed by their interdependence upon one another. Negotiation provides a solution to these problems by giving the agents the means to resolve their conflicting objectives, correct inconsistencies in their knowledge of other agents' world views, and coordinate a joint approach to domain tasks which benefits all the agents concerned. We propose a framework, based upon a system of argumentation, which permits agents to negotiate in order to establish acceptable ways of solving problems. The framework provides a formal model of argumentation-based reasoning and negotiation, details a design philosophy which ensures a clear link between the formal model and its practical instantiation, and describes a case study of this relationship for a particular class of architectures (namely those for belief-desire-intention agents).

The Knowledge Level (KL) is an abstract level of description, prior to the symbol or software level, which aims at discovering the components of expertise without thinking of computational aspects. The KL analysis emphasizes the regularities in knowledge use for knowledge engineering. We consider the knowledge level analysis the AI counterpart of the specification of programs. Then, it must be possible to define formal ways of putting in relation the KL analysis with computational elements that implement it. The ultimate goal of the research presented in this article is to contribute in the filling of the gap between specification at the KL and implementation. To do so we propose (i) a particular interpretation of the three main concepts involved in the knowledge level theories, i.e., tasks, methods, and domain models, and (ii) a mapping between these notions and computational elements of Milord II, a shell developed at the IIIA Institute and used as the target programming environment of an example in biological identification. © 1997 John Wiley & Sons, Inc.

. In this paper we describe an approach to the problem of dealing with uncertainty by means of finite multi-valued logics in modular expert systems, and the results obtained. The modularity of the systems allows us to address two main characteristics of human problem-solving: the adaptation of general knowledge to particular problems and the dependency of the management of uncertainty on the different subtasks being implemented in the modules of the system, i.e. different modules can have different local multiple-valued logics as part of their local deductive mechanisms. Although the results obtained are general, we use, throughout the paper, examples of a medical expert system that has been designed using a modular language called MILORD-II, that implements them showing the practical interest of the theoretical concepts involved.