CJ

C.M. Jonker

info

Please Note

212 records found

Conference paper (2026) - Mireia Yurrita, Davide Dell’Anna, Pradeep K. Murukannaiah, Catholijn M. Jonker, Pınar Yolum
Agents based on Large Language Models (LLM agents) have the potential to work with humans as part of a team to achieve specific goals. The natural language interface of LLM agents and their high level of autonomy enables more seamless collaborations than previous technologies, allowing them to carry out tasks autonomously and engage in conversations with humans, e.g., to clarify goals, request authorizations, or double-check decisions. However, the current literature lacks systematic design guidelines for these human-LLM agent teams. This gap might foster misunderstandings, misuse of autonomy, and lack of common ground, potentially leading to collaboration pitfalls. To mitigate these risks, we develop 24 guidelines for the principled design of human-LLM agent teams. We adopt a multi-stakeholder approach and propose guidelines for LLM agents, human team members, team designers and embedding organizations. To develop these guidelines, we distill design recommendations from an exploratory workshop with 15 experts on human-AI teaming and a literature review of 93 empirical papers in human-LLM collaboration. Drawing from literature on human teams, we conceptually categorize the recommendations across different stages of the teaming process. A user study with 10 additional experts suggests the guidelines can help prevent collaboration pitfalls in human-LLM agent teams within workplace settings. ...

A Conversational Agent for Adaptive Decision-Making Support Through System 1 and System 2 Thinking

Making high-stakes personal decisions involves cognitive, emotional, and intuitive processes, and individuals differ in how they allocate attention across these modes. Integration of these processes has shown to benefit decision making. Yet, most current decision-support systems focus primarily on supporting cognitive aspects, rather than adapting to the individual's thinking profile to support integration of different types of thoughts. In this study, we investigate an agent designed to encourage integration by adapting to the individual user's thought patterns. We explore its effects on participants' perceptions of the agent and their reflective behavior, in comparison with unaided pre-reflection and a baseline agent. In a between-subjects study (N = 128), our agent, which fostered broad and elaborated thinking, enabled more personalized reflective trajectories, elicited more integrative reflective language, and was perceived as providing stronger support for holistic reflection. In contrast, the baseline agent produced homogenized profiles dominated by cognitive language across participants. ...

Does Model Size Matter in Human-AI Collaborations?

Conference paper (2026) - Lennard C. Froma, Tom Kouwenhoven, Maaike H.T. De Boer, Catholijn M. Jonker, Max J. Van Duijn
Much research on LLMs has focused on increasing benchmark performance. However, the evaluation of such models in real-world collaborative human-AI workflows has stayed behind. This work evaluates a chatbot-style assistant based on Retrieval-Augmented Generation (RAG) in a realistic multi-turn information-seeking scenario inspired by workplace settings where compliance with local legislation and secure handling of sensitive data are often key. Specifically, we examine the performance of humans (N=112) assisted by RAG-assistants compared to LLM-only or LLM+RAG baselines. In this setting, we investigate how underlying model size (3B, 8B, and 70B) shapes the human-AI collaborative dynamic and how it influences perceived usability and satisfaction. Results show that the performance gain of human-AI collaboration over the model-only baselines is significant, irrespective of model size, suggesting that hybrid systems are beneficial in information-seeking scenarios. Interestingly, however, perceived usability and satisfaction among participants showed little difference across model sizes. This demonstrates a nuanced trade-off between model size, performance, and user perception. Our work highlights the added value of evaluating AI applications in actual multi-turn interactions with human users, looking at usability and satisfaction besides accuracy, rather than focusing on benchmark performance only. ...

Identifying, characterizing, and evaluating foundational quality attributes

Journal article (2026) - Davide Dell’Anna, Pradeep K. Murukannaiah, Mireia Yurrita, Bernd Dudzik, Davide Grossi, Catholijn M. Jonker, Catharine Oertel, Pınar Yolum
Hybrid Intelligence (HI) is an emerging paradigm in which artificial intelligence (AI) augments human intelligence. The current literature lacks systematic models that guide the design and evaluation of HI systems. Further, discussions around HI primarily focus on technology, neglecting the holistic human-AI ensemble. In this paper, we take the initial steps toward the development of a quality model for characterizing and evaluating HI systems from a human-AI teams perspective. We first conducted a study investigating the adequacy of properties commonly associated with effective human teams to describe HI. The study features the insights of 50 HI researchers, and shows that various human team properties, including boundedness, interdependence, competency, purposefulness, initiative, normativity, and effectiveness, are important for HI systems. Based on these results, we developed a quality model for HI teams composed of seven high-level quality attributes, further refined into 16 specific ones. To evaluate the relevance and understanding of the proposed attributes, we conducted a second empirical investigation by staging competitions in which participants used the quality model to develop and analyze HI usage scenarios. Our analysis of 48 collected scenarios, which we openly release, confirms the proposed attributes’ relevance and highlights insights that emerge when designers consider the quality model in HI system design. ...
Conference paper (2025) - Stephanie Tan, Wendy M. Aartsen, Dicky van Hamersveld, Catholijn M. Jonker
The roles of humans and AI as the labor force of organizations need continuous re-evaluation with the advancement of AI. While automation has replaced some tasks, knowledge-intensive work environments rely on human intelligence, as those work practices transcend canonical procedures. We propose a hybrid intelligence methodology for organizations to address knowledge erosion. We contextualize this methodology in an example case study from the Legal Desk in the Netherlands, following the six principles of designing intelligent organizations [1], i.e., addition, relevance, substitution, diversity, collaboration, and explanation. We found that adhering to these six basic principles appeared to be a balancing act on two axes: contribution of AI versus human intelligence towards the tasks, and the way of working of human and artificial agents over time. We propose two additional principles. The first is human oversight, which highlights the importance of human control in organizational decision-making. The second principle is collaborative reflection which emphasizes the need to actively manage organizational intelligence. We also discuss the challenges to enable our methodology in the organizational context. This paper aims to inspire researchers and practitioners to pursue new initiatives towards achieving hybrid intelligence for learning organizations. ...
Journal article (2025) - P.Y. Chen, M. Birna van Riemsdijk, Dirk K.J. Heylen, C.M. Jonker, M.L. Tielman
Effective support from personal assistive technologies relies on accurate user models that capture user values, preferences, and context. Knowledge-based techniques model these relationships, enabling support agents to align their actions with user values. However, understanding values in a single context is insufficient due to the dynamic nature of behaviour. This study explores the use of dialogue strategies to update user models. Participants were randomly assigned to different strategies and they discussed one randomly chosen non-adherence situation with the agent. Then, their emotions, acquired information accuracy, completeness, and dialogue experience were rated. Our findings suggest that multiple-choice dialogues may limit response depth, reducing the perceived completeness of behaviour reasons. In contrast, open-ended questions allow more detailed input but require more time and effort, potentially worsening the dialogue experience. Through inductive coding, we identified key topics, such as individual challenges, priorities, tangible outcomes, and values, essential for constructing personalised user models. We also analyzed conversation paths to improve dialogue-based user model updates in support agents. Further research is needed to refine the relationship between dialogue strategies and self-conscious emotions, considering diverse backgrounds and health goals, while enhancing dialogue design. ...
In today's society, where Artificial Intelligence (AI) has gained a vital role, concerns regarding user's trust have garnered significant attention. The use of AI systems in high-risk domains have often led users to either under-trust it, potentially causing inadequate reliance or over-trust it, resulting in over-compliance. Therefore, users must maintain an appropriate level of trust. Past research has indicated that explanations provided by AI systems can enhance user understanding of when to trust or not trust the system. However, the utility of presentation of different explanations forms still remains to be explored especially in high-risk domains. Therefore, this study explores the impact of different explanation types (text, visual, and hybrid) and user expertise (retired police officers and lay users) on establishing appropriate trust in AI-based predictive policing. While we observed that the hybrid form of explanations increased the subjective trust in AI for expert users, it did not led to better decision-making. Furthermore, no form of explanations helped build appropriate trust. The findings of our study emphasize the importance of re-evaluating the use of explanations to build [appropriate] trust in AI based systems especially when the system's use is questionable. Finally, we synthesize potential challenges and policy recommendations based on our results to design for appropriate trust in high-risk based AI-based systems. ...

How Should We Design Agent-Mediated Mimicry?

A lack of self-awareness of communicative behaviours can lead to disadvantages in important interactions. Video recordings as a tool for self-observation have been widely adopted to initiate behaviour change and reflection. Seeing oneself in a recording can lead to negative affect. Forcing an external perspective can lead to cognitive dissonance. Avatars and virtual agents have the advantage that they can copy a human's behaviour while potentially avoiding this dissonance. To explore the design space of mimicking agents, we set up a user study where a video baseline is compared to agent-mediated conditions ranging from idle non-verbal behaviour to complete mimicry of the voice and face. We show that participants gain increased self-awareness from seeing themselves mediated through the virtual agent. We further discuss qualitative observations for the future design of systems that aid in self-reflection, and particularly note that partial mimicry seems to be less appreciated than full mimicry. ...
Conference paper (2025) - Reyhan Aydoğan, Tim Baarslag, Tamara C.P. Florijn, Katsuhide Fujita, Catholijn M. Jonker, Yasser Mohammad
This paper introduces the main research challenges and results of the 15th International Automated Negotiating Agents Competition (ANAC 2024). The main challenges addressed are learning the reservation value in bilateral negotiation and designing a factory agent employing concurrent negotiation in supply chain management. Additionally, it outlines the future directions for the competition. ...
Understanding citizens’ values in participatory systems is crucial for citizen-centric policy-making. We envision a hybrid participatory system where participants make choices and provide motivations for those choices, and AI agents estimate their value preferences by interacting with them. We focus on situations where a conflict is detected between participants’ choices and motivations, and propose methods for estimating value preferences while addressing detected inconsistencies by interacting with the participants. We operationalize the philosophical stance that “valuing is deliberatively consequential.” That is, if a participant’s choice is based on a deliberation of value preferences, the value preferences can be observed in the motivation the participant provides for the choice. Thus, we propose and compare value preferences estimation methods that prioritize the values estimated from motivations over the values estimated from choices alone. Then, we introduce a disambiguation strategy that combines Natural Language Processing and Active Learning to address the detected inconsistencies between choices and motivations. We evaluate the proposed methods on a dataset of a large-scale survey on energy transition. The results show that explicitly addressing inconsistencies between choices and motivations improves the estimation of an individual’s value preferences. The disambiguation strategy does not show substantial improvements when compared to similar baselines—however, we discuss how the novelty of the approach can open new research avenues and propose improvements to address the current limitations. ...
Mutual trust between humans and interactive artificial agents is crucial for effective human-agent teamwork. This involves not only the human appropriately trusting the artificial teammate, but also the artificial teammate assessing the human’s trustworthiness for different tasks (i.e., artificial trust in human partners). Literature indicated that transparency and explainability is generally beneficial for human-agent collaboration. However, communicating artificial trust potentially affects human trust and satisfaction, which impact team dynamics. Towards studying these effects, we developed an artificial trust model and implemented five distinct communication approaches which varied in modality (visual/graphical and/or text), level (communication and/or explanation), and timing (real-time or occasional). We evaluated the effects of the different communication styles through a user study (N=120) in a 2D grid-world Search and Rescue scenario. Our results show that all our artificial trust explanations improved human trust and satisfaction, but the mere graphical communication of it did not. These results are bound to the specific scenario and context in which this study was run and require further exploration. As such, this work presents a first step towards understanding the consequences of communicating and explaining to a human teammate their assessed trustworthiness. ...
Aggregating multiple annotations into a single ground truth label may hide valuable insights into annotator disagreement, particularly in tasks where subjectivity plays a crucial role. In this work, we explore methods for identifying subjectivity in recognizing the human values that motivate arguments. We evaluate two main approaches: inferring subjectivity through value prediction vs. directly identifying subjectivity. Our experiments show that direct subjectivity identification significantly improves the model performance of flagging subjective arguments. Furthermore, combining contrastive loss with binary cross-entropy loss does not improve performance but reduces the dependency on per-label subjectivity. Our proposed methods can help identify arguments that individuals may interpret differently, fostering a more nuanced annotation process. ...
Combating widespread misinformation requires scalable and reliable fact-checking methods. Fact-checking involves several steps, including question generation, evidence retrieval, and veracity prediction. Importantly, fact-checking is well-suited to exploit hybrid intelligence since it requires both human expertise and AI’s large-scale information processing abilities. Thus, constructing an effective fact-checking pipeline requires a systematic understanding of the relative strengths and weaknesses of humans and AI in different steps of the fact-checking process. We investigate the ability of LLMs to perform the first step of the process, i.e., to generate pertinent questions for analyzing a claim. To evaluate the quality of the LLM-generated questions, we crowdsource a dataset in which 150 claims are annotated with questions (1) a novice fact-checker would ask and (2) a professional fact-checker would ask when fact-checking those claims. We study the effects of the human- and LLM-generated questions on evidence retrieval and veracity prediction. We find that LLMs are able to generate nuanced questions to verify a complex claim, but the final label prediction depends on the quality of the evidence corpus. However, the evidence collected by automated methods yields lower accuracy in the veracity prediction task than the evidence curated by experts. ...
As human-machine teams become a more common scenario, we need to ensure mutual trust between humans and machines. More important than having trust, we need all teammates to trust each other appropriately. This means that they should not overtrust or undertrust each other, avoiding risks and inefficiencies, respectively. We usually think of natural trust, that is, humans trusting machines, but we should also consider artificial trust, that is, artificial agents trusting humans. Appropriate artificial trust allows the agents to interpret human behavior and predict their behavior in a certain context. In this chapter, we explore how we can define this context in terms of task and team characteristics. We present a taxonomy that shows how trust is context-dependent. In fact, we propose that no trust model presented in the literature fits all contexts and argue that our taxonomy facilitates the choice of the trust model that better fits a certain context. The taxonomy helps to understand which internal characteristics of the teammate (krypta) are important to consider and how they will show in behavior cues (manifesta). This taxonomy can also be used to help human-machine teams’ researchers in the problem definition and process of experimental design as it allows a detailed characterization of the task and team configuration. Furthermore, we propose a formalization of the belief of trust as context-dependent trustworthiness, and show how beliefs of trust can be used to reach appropriate trust. Our work provides a starting point to implement mutual appropriate trust in human-machine teams. ...

Exploring the dynamics of the “subsidy tables” approach in Dutch social care delivery

Journal article (2024) - Floor Kist, Hans de Bruijn, Catholijn Jonker
Purpose: The objective of this paper is to develop a redesigned commissioning process for social care services that fosters integrated care, encourages collaboration and balances professional expertise with client engagement. Design/methodology/approach: This study employs a two-pronged approach: a case study of a municipality’s use of subsidy tables and a literature scoping review on integrated care research. Findings: The paper introduces a new framework for the study of the new “subsidy tables.” A well-defined and extensive consultation process involving both social care providers (suppliers), the Service Triad, and client representation adds to the existing research on supplier consultation, and on how to define the outcomes for clients via client engagement. Research limitations/implications: While aspects are clearly relevant to the Netherlands, the design of the commissioning process of social care has international relevance as well: finding definitions, formulating outcomes and incentives, designing a more collaborative instead of competitive process, stakeholder engagement and consultation. Practical implications: Several Dutch municipalities started using the “subsidy tables” method for commissioning integrated social care. This paper offers clear improvements that benefit the commissioners, the social care providers and their clients. Social implications: Improving the commissioning process of integrated social care will lead to better fitting care for people who need social care. Originality/value: This paper is one of the first to do a thorough analysis of the “subsidy tables” method for commissioning integrated social care. ...

A framework for human–machine team design

As machines' autonomy increases, the possibilities for collaboration between a human and a machine also increase. In particular, tasks may be performed with varying levels of interdependence, i.e. from independent to joint actions. The feasibility of each type of interdependence depends on factors that contribute to contextual trustworthiness, such as team members' competence, willingness and external factors. In this paper, we present the Interdependence and Trust Analysis (ITA) framework, which is an extension of Coactive Design's Interdependence Analysis framework (Johnson, M., J. M. Bradshaw, P. J. Feltovich, C. M. Jonker, M. Birna Van Riemsdijk, M. Sierhuis. 2014. Coactive Design: Designing Support for Interdependence in Joint Activity. Journal of Human-Robot Interaction 3 (1): 43–69. https://doi.org/10.5898/JHRI.3.1.Johnson). By including information on contextual trustworthiness, ITA can better support the design of human–machine teams, as well as task allocation and selection. Evaluated through expert interviews and a focus group involving a search and rescue scenario, ITA shows potential as a decision-making tool and a communication bridge among human and machine teammates. Our findings emphasise the need to define tasks and roles based on agent characteristics, and imply that decision-making models should align with human-centred objectives. ITA also highlights the trade-off between utility and effort when designing trustworthy systems, suggesting that guided conversations could improve the team design process. Finally, the ITA framework may improve transparency, justification, and interpretability in decision-making, contributing to appropriate trust among teammates. ...
Conference paper (2024) - C. Centeio Jorge, Ewart J. de Visser, M.L. Tielman, C.M. Jonker, Lionel P. Robert
As machines' autonomy increases, their capacity to learn and adapt to humans in collaborative scenarios increases too. In particular, machines can use artificial trust (AT) to make decisions, such as task and role allocation/selection. However, the outcome of such decisions and the way these are communicated can affect the human's trust, which in turn affects how the human collaborates too. With the goal of maintaining mutual appropriate trust between the human and the machine in mind, we reflect on the requirements for having an AT-based decision-making model on an artificial teammate. Furthermore, we propose a user study to investigate the role of task-based willingness (e.g. human preferences on tasks) and its communication in AT-based decision-making. ...
Relevancy is a prevalent term in value alignment. We either need to keep track of the relevant moral reasons, we need to embed the relevant values, or we need to learn from the relevant behaviour. What relevancy entails in particular cases, however, is often ill-defined. The reasons for this are obvious, it is hard to define relevancy in a way that is both general and concrete enough to give direction towards a specific implementation. In this paper, we describe the inherent difficulty that comes along with defining what is relevant to a particular situation. Simply due to design and the way an AI system functions, we need to state or learn particular goals and circumstances under which that goal is completed. However, because of both the changing nature of the world and the varied wielders and users of such implements, misalignment occurs, especially after a longer amount of time. We propose a way to counteract this by putting contestability front and centre throughout the lifecycle of an AI system, as it can provide insight into what is actually relevant at a particular instance. This allows designers to update the applications in such a manner that they can account for oversight during design. ...
Conference paper (2024) - Jakob Dirk Top, Catholijn Jonker, Rineke Verbrugge, Harmen de Weerd
Epistemic logic can be used to reason about statements such as ‘I know that you know that I know that φ ’. In this logic, and its extensions, it is commonly assumed that agents can reason about epistemic statements of arbitrary nesting depth. In contrast, empirical findings on Theory of Mind, the ability to (recursively) reason about mental states of others, show that human recursive reasoning capability has an upper bound. In the present paper we work towards resolving this disparity by proposing some elements of a logic of bounded Theory of Mind, built on Public Announcement Logic. Using this logic, and a statistical method called Random-Effects Bayesian Model Selection, we estimate the distribution of Theory of Mind levels in the participant population of a previous behavioral experiment. Despite not modeling stochastic behavior, we find that approximately three-quarters of participants’ decisions can be described using Theory of Mind. In contrast to previous empirical research, our models estimate the majority of participants to be second-order Theory of Mind users. ...
Journal article (2024) - C. Centeio Jorge, C.M. Jonker, M.L. Tielman
In teams composed of humans, we use trust in others to make decisions, such as what to do next, who to help and who to ask for help. When a team member is artificial, they should also be able to assess whether a human teammate is trustworthy for a certain task. We see trustworthiness as the combination of (1) whether someone will do a task and (2) whether they can do it. With building beliefs in trustworthiness as an ultimate goal, we explore which internal factors (krypta) of the human may play a role (e.g., ability, benevolence, and integrity) in determining trustworthiness, according to existing literature. Furthermore, we investigate which observable metrics (manifesta) an agent may take into account as cues for the human teammate’s krypta in an online 2D grid-world experiment (n = 54). Results suggest that cues of ability, benevolence and integrity influence trustworthiness. However, we observed that trustworthiness is mainly influenced by human’s playing strategy and cost-benefit analysis, which deserves further investigation. This is a first step towards building informed beliefs of human trustworthiness in human-AI teamwork. ...