Nir Oren

Adarsa Sivaprasad, Ehud Reiter, Nava Tintarev et al.

In explainable artificial intelligence (XAI) research, the predominant focus has been on interpreting models for experts and practitioners. Model agnostic and local explanation approaches are deemed interpretable and sufficient in many applications. However, in domains like healthcare, where end users are patients without AI or domain expertise, there is an urgent need for model explanations that are more comprehensible and instil trust in the model's operations. We hypothesise that generating model explanations that are narrative, patient-specific and global(holistic of the model) would enable better understandability and enable decision-making. We test this using a decision tree model to generate both local and global explanations for patients identified as having a high risk of coronary heart disease. These explanations are presented to non-expert users. We find a strong individual preference for a specific type of explanation. The majority of participants prefer global explanations, while a smaller group prefers local explanations. A task based evaluation of mental models of these participants provide valuable feedback to enhance narrative global explanations. This, in turn, guides the design of health informatics systems that are both trustworthy and actionable.

Nir Oren, Bruno Yun, Assaf Libman et al.

Gradual semantics within abstract argumentation associate a numeric score with every argument in a system, which represents the level of acceptability of this argument, and from which a preference ordering over arguments can be derived. While some semantics operate over standard argumentation frameworks, many utilise a weighted framework, where a numeric initial weight is associated with each argument. Recent work has examined the inverse problem within gradual semantics. Rather than determining a preference ordering given an argumentation framework and a semantics, the inverse problem takes an argumentation framework, a gradual semantics, and a preference ordering as inputs, and identifies what weights are needed to over arguments in the framework to obtain the desired preference ordering. Existing work has attacked the inverse problem numerically, using a root finding algorithm (the bisection method) to identify appropriate initial weights. In this paper we demonstrate that for a class of gradual semantics, an analytical approach can be used to solve the inverse problem. Unlike the current state-of-the-art, such an analytic approach can rapidly find a solution, and is guaranteed to do so. In obtaining this result, we are able to prove several important properties which previous work had posed as conjectures.

Nir Oren, Bruno Yun

A gradual semantics takes a weighted argumentation framework as input and outputs a final acceptability degree for each argument, with different semantics performing the computation in different manners. In this work, we consider the problem of attack inference. That is, given a gradual semantics, a set of arguments with associated initial weights, and the final desirable acceptability degrees associated with each argument, we seek to determine whether there is a set of attacks on those arguments such that we can obtain these acceptability degrees. The main contribution of our work is to demonstrate that the associated decision problem, i.e., whether a set of attacks can exist which allows the final acceptability degrees to occur for given initial weights, is NP-complete for the weighted h-categoriser and cardinality-based semantics, and is polynomial for the weighted max-based semantics, even for the complete version of the problem (where all initial weights and final acceptability degrees are known). We then briefly discuss how this decision problem can be modified to find the attacks themselves and conclude by examining the partial problem where not all initial weights or final acceptability degrees may be known.

Bruno Yun, Nir Oren, Madalina Croitoru

In this paper, we place ourselves in the context of human robot interaction and address the problem of cognitive robot modelling. More precisely we are investigating properties of a utility-based model that will govern a robot's actions. The novelty of this approach lies in embedding the responsibility of the robot over the state of affairs into the utility model via a utility aggregation function. We describe desiderata for such a function and consider related properties.

Kin Max Piamolini Gusmão, Nathan Gavenski, Nir Oren et al.

Large language models have recently reached near-parity with classical planners on well-known planning domains, yet this competence relies on world-knowledge exploitation rather than genuine symbolic reasoning. Goal recognition is a complementary abductive task structurally better suited to LLM strengths: it consists of evaluating consistency with world knowledge rather than generating novel action sequences. This paper provides the first systematic zero-shot evaluation of frontier LLMs as goal recognisers on key classical PDDL benchmarks. Our results show that LLM competence on goal recognition is uneven: some models scale with evidence and approach landmark-based accuracy at full observations, while others remain anchored to world-knowledge priors regardless of how much evidence accumulates. Qualitative analysis of model reasoning traces reveals that this divergence reflects a fundamental difference in evidence integration rather than domain familiarity. These findings position goal recognition as a principled benchmark for the foundational planning knowledge of LLMs.

Alessio Zaninotto, Bruno Yun, Nir Oren et al.

Preference-based argumentation frameworks (PAFs) extend Dung's approach to abstract argumentation (AAFs) by encoding preferences over arguments. Such preferences control the transformation of attacks into defeats, and different approaches to doing so result in different reductions from a PAF to an AAF. In this paper we consider a PAF inverse problem which takes an argumentation graph, a labelling and a semantics as an input, and outputs a ``yes" or ``no" as to whether there is a preference relation between the arguments which can yield the desired labelling. This inverse problem has applications in areas including preference elicitation and explainability. We consider this problem in the context of the four most widely-used preference based reductions under the complete semantics. We show that in most cases, the problem can be answered in polynomial time.

Stephen Cranefield, Nir Oren

AI systems are becoming increasingly complex, ubiquitous and autonomous, leading to increasing concerns about their impacts on individuals and society. In response, researchers have begun investigating how to ensure that the methods underlying AI decision-making are transparent and their decisions are explainable to people and conformant to human values and ethical principles. As part of this research thrust, the need for accountability within AI systems has been noted, but this notion has proven elusive to define; we aim to address this issue in the current paper. Unlike much recent work, we do not address accountability within the human organisational processes of developing and deploying AI; rather we consider what it would it mean for the agents within a multi-agent system (MAS), potentially including human agents, to be accountable to other agents or to have others accountable to them. In this work, we make the following contributions: we provide an in-depth survey of existing work on accountability in multiple disciplines, seeking to identify a coherent definition of the concept; we give a realistic example of a multi-agent system application domain that illustrates the benefits of enabling agents to follow accountability processes, and we identify a set of research challenges for the MAS community in building accountable agents, sketching out some initial solutions to these, thereby laying out a road-map for future research. Our focus is on laying the groundwork to enable autonomous elements within open socio-technical systems to take part in accountability processes.

Nir Oren, Bruno Yun

Many semantics for weighted argumentation frameworks assume that each argument is associated with an initial weight. However, eliciting these initial weights poses challenges: (1) accurately providing a specific numerical value is often difficult, and (2) individuals frequently confuse initial weights with acceptability degrees in the presence of other arguments. To address these issues, we propose an elicitation pipeline that allows one to specify acceptability degree intervals for each argument. By employing gradual semantics, we can refine these intervals when they are rational, restore rationality when they are not, and ultimately identify possible initial weights for each argument.

Bradley Scott, Clarisse de Vries, Aiden Durrant et al.

In this study, we investigated whether transfer learning from macaque monkeys could improve human pose estimation. Current state-of-the-art pose estimation techniques, often employing deep neural networks, can match human annotation in non-clinical datasets. However, they underperform in novel situations, limiting their generalisability to clinical populations with pathological movement patterns. Clinical datasets are not widely available for AI training due to ethical challenges and a lack of data collection. We observe that data from other species may be able to bridge this gap by exposing the network to a broader range of motion cues. We found that utilising data from other species and undertaking transfer learning improved human pose estimation in terms of precision and recall compared to the benchmark, which was trained on humans only. Compared to the benchmark, fewer human training examples were needed for the transfer learning approach (1,000 vs 19,185). These results suggest that macaque pose estimation can improve human pose estimation in clinical situations. Future work should further explore the utility of pose estimation trained with monkey data in clinical populations.

Chunyan Mu, Nir Oren

We introduce a family of quantitative measures of responsibility in multi-agent planning, building upon the concepts of causal responsibility proposed by Parker et al.~[ParkerGL23]. These concepts are formalised within a variant of probabilistic alternating-time temporal logic. Unlike existing approaches, our framework ascribes responsibility to agents for a given outcome by linking probabilities between behaviours and responsibility through three metrics, including an entropy-based measurement of responsibility. This latter measure is the first to capture the causal responsibility properties of outcomes over time, offering an asymptotic measurement that reflects the difficulty of achieving these outcomes. Our approach provides a fresh understanding of responsibility in multi-agent systems, illuminating both the qualitative and quantitative aspects of agents' roles in achieving or preventing outcomes.

Chunyan Mu, Muhammad Najib, Nir Oren

Responsibility plays a key role in the development and deployment of trustworthy autonomous systems. In this paper, we focus on the problem of strategic reasoning in probabilistic multi-agent systems with responsibility-aware agents. We introduce the logic PATL+R, a variant of Probabilistic Alternating-time Temporal Logic. The novelty of PATL+R lies in its incorporation of modalities for causal responsibility, providing a framework for responsibility-aware multi-agent strategic reasoning. We present an approach to synthesise joint strategies that satisfy an outcome specified in PATL+R, while optimising the share of expected causal responsibility and reward. This provides a notion of balanced distribution of responsibility and reward gain among agents. To this end, we utilise the Nash equilibrium as the solution concept for our strategic reasoning problem and demonstrate how to compute responsibility-aware Nash equilibrium strategies via a reduction to parametric model checking of concurrent stochastic multi-player games.

Quratul-ain Mahesar, Nir Oren, Wamberto W. Vasconcelos

We present an extension-based approach for computing and verifying preferences in an abstract argumentation system. Although numerous argumentation semantics have been developed previously for identifying acceptable sets of arguments from an argumentation framework, there is a lack of justification behind their acceptability based on implicit argument preferences. Preference-based argumentation frameworks allow one to determine what arguments are justified given a set of preferences. Our research considers the inverse of the standard reasoning problem, i.e., given an abstract argumentation framework and a set of justified arguments, we compute what the possible preferences over arguments are. Furthermore, there is a need to verify (i.e., assess) that the computed preferences would lead to the acceptable sets of arguments. This paper presents a novel approach and algorithm for exhaustively computing and enumerating all possible sets of preferences (restricted to three identified cases) for a conflict-free set of arguments in an abstract argumentation framework. We prove the soundness, completeness and termination of the algorithm. The research establishes that preferences are determined using an extension-based approach after the evaluation phase (acceptability of arguments) rather than stated beforehand. In this work, we focus our research study on grounded, preferred and stable semantics. We show that the complexity of computing sets of preferences is exponential in the number of arguments, and thus, describe an approximate approach and algorithm to compute the preferences. Furthermore, we present novel algorithms for verifying (i.e., assessing) the computed preferences. We provide details of the implementation of the algorithms (source code has been made available), various experiments performed to evaluate the algorithms and the analysis of the results.

Assaf Libman, Nir Oren, Bruno Yun

Weighted gradual semantics provide an acceptability degree to each argument representing the strength of the argument, computed based on factors including background evidence for the argument, and taking into account interactions between this argument and others. We introduce four important problems linking gradual semantics and acceptability degrees. First, we reexamine the inverse problem, seeking to identify the argument weights of the argumentation framework which lead to a specific final acceptability degree. Second, we ask whether the function mapping between argument weights and acceptability degrees is injective or a homeomorphism onto its image. Third, we ask whether argument weights can be found when preferences, rather than acceptability degrees for arguments are considered. Fourth, we consider the topology of the space of valid acceptability degrees, asking whether "gaps" exist in this space. While different gradual semantics have been proposed in the literature, in this paper, we identify a large family of weighted gradual semantics, called abstract weighted based gradual semantics. These generalise many of the existing semantics while maintaining desirable properties such as convergence to a unique fixed point. We also show that a sub-family of the weighted gradual semantics, called abstract weighted (L^p,λ,μ)-based gradual semantics and which include well-known semantics, solve all four of the aforementioned problems.

Nir Oren, Bruno Yun, Srdjan Vesic et al.

Gradual semantics with abstract argumentation provide each argument with a score reflecting its acceptability, i.e. how "much" it is attacked by other arguments. Many different gradual semantics have been proposed in the literature, each following different principles and producing different argument rankings. A sub-class of such semantics, the so-called weighted semantics, takes, in addition to the graph structure, an initial set of weights over the arguments as input, with these weights affecting the resultant argument ranking. In this work, we consider the inverse problem over such weighted semantics. That is, given an argumentation framework and a desired argument ranking, we ask whether there exist initial weights such that a particular semantics produces the given ranking. The contribution of this paper are: (1) an algorithm to answer this problem, (2) a characterisation of the properties that a gradual semantics must satisfy for the algorithm to operate, and (3) an empirical evaluation of the proposed algorithm.

Nir Oren, Felipe Meneguzzi

Societal rules, as exemplified by norms, aim to provide a degree of behavioural stability to multi-agent societies. Norms regulate a society using the deontic concepts of permissions, obligations and prohibitions to specify what can, must and must not occur in a society. Many implementations of normative systems assume various combinations of the following assumptions: that the set of norms is static and defined at design time; that agents joining a society are instantly informed of the complete set of norms; that the set of agents within a society does not change; and that all agents are aware of the existing norms. When any one of these assumptions is dropped, agents need a mechanism to identify the set of norms currently present within a society, or risk unwittingly violating the norms. In this paper, we develop a norm identification mechanism that uses a combination of parsing-based plan recognition and Hierarchical Task Network (HTN) planning mechanisms, which operates by analysing the actions performed by other agents. While our basic mechanism cannot learn in situations where norm violations take place, we describe an extension which is able to operate in the presence of violations.

Bruno Yun, Srdjan Vesic, Nir Oren

In this paper we describe an argumentation-based representation of normal form games, and demonstrate how argumentation can be used to compute pure strategy Nash equilibria. Our approach builds on Modgil's Extended Argumentation Frameworks. We demonstrate its correctness, prove several theoretical properties it satisfies, and outline how it can be used to explain why certain strategies are Nash equilibria to a non-expert human user.

Quratul-ain Mahesar, Nir Oren, Wamberto W. Vasconcelos

Various structured argumentation frameworks utilize preferences as part of their standard inference procedure to enable reasoning with preferences. In this paper, we consider an inverse of the standard reasoning problem, seeking to identify what preferences over assumptions could lead to a given set of conclusions being drawn. We ground our work in the Assumption-Based Argumentation (ABA) framework, and present an algorithm which computes and enumerates all possible sets of preferences over the assumptions in the system from which a desired conflict free set of conclusions can be obtained under a given semantic. After describing our algorithm, we establish its soundness, completeness and complexity.

Ramon Fraga Pereira, Nir Oren, Felipe Meneguzzi

The task of recognizing goals and plans from missing and full observations can be done efficiently by using automated planning techniques. In many applications, it is important to recognize goals and plans not only accurately, but also quickly. To address this challenge, we develop novel goal recognition approaches based on planning techniques that rely on planning landmarks. In automated planning, landmarks are properties (or actions) that cannot be avoided to achieve a goal. We show the applicability of a number of planning techniques with an emphasis on landmarks for goal and plan recognition tasks in two settings: (1) we use the concept of landmarks to develop goal recognition heuristics; and (2) we develop a landmark-based filtering method to refine existing planning-based goal and plan recognition approaches. These recognition approaches are empirically evaluated in experiments over several classical planning domains. We show that our goal recognition approaches yield not only accuracy comparable to (and often higher than) other state-of-the-art techniques, but also substantially faster recognition time over such techniques.

Ramon Fraga Pereira, Nir Oren, Felipe Meneguzzi

Assessing whether an agent has abandoned a goal or is actively pursuing it is important when multiple agents are trying to achieve joint goals, or when agents commit to achieving goals for each other. Making such a determination for a single goal by observing only plan traces is not trivial as agents often deviate from optimal plans for various reasons, including the pursuit of multiple goals or the inability to act optimally. In this article, we develop an approach based on domain independent heuristics from automated planning, landmarks, and fact partitions to identify sub-optimal action steps - with respect to a plan - within a plan execution trace. Such capability is very important in domains where multiple agents cooperate and delegate tasks among themselves, e.g. through social commitments, and need to ensure that a delegating agent can infer whether or not another agent is actually progressing towards a delegated task. We demonstrate how an agent can use our technique to determine - by observing a trace - whether an agent is honouring a commitment. We empirically show, for a number of representative domains, that our approach infers sub-optimal action steps with very high accuracy and detects commitment abandonment in nearly all cases.

Juan Afanador, Nir Oren, Murilo S. Baptista

Delegation allows an agent to request that another agent completes a task. In many situations the task may be delegated onwards, and this process can repeat until it is eventually, successfully or unsuccessfully, performed. We consider policies to guide an agent in choosing who to delegate to when such recursive interactions are possible. These policies, based on quitting games and multi-armed bandits, were empirically tested for effectiveness. Our results indicate that the quitting game based policies outperform those which do not explicitly account for the recursive nature of delegation.

Beishui Liao, Nir Oren, Leendert van der Torre et al.

To resolve conflicts among norms, various nonmonotonic formalisms can be used to perform prioritized normative reasoning. Meanwhile, formal argumentation provides a way to represent nonmonotonic logics. In this paper, we propose a representation of prioritized normative reasoning by argumentation. Using hierarchical abstract normative systems, we define three kinds of prioritized normative reasoning approaches, called Greedy, Reduction, and Optimization. Then, after formulating an argumentation theory for a hierarchical abstract normative system, we show that for a totally ordered hierarchical abstract normative system, Greedy and Reduction can be represented in argumentation by applying the weakest link and the last link principles respectively, and Optimization can be represented by introducing additional defeats capturing the idea that for each argument that contains a norm not belonging to the maximal obeyable set then this argument should be rejected.

Zimi Li, Nir Oren, Simon Parsons

In this paper we investigate the links between instantiated argumentation systems and the axioms for non-monotonic reasoning described in [9] with the aim of characterising the nature of argument based reasoning. In doing so, we consider two possible interpretations of the consequence relation, and describe which axioms are met by ASPIC+ under each of these interpretations. We then consider the links between these axioms and the rationality postulates. Our results indicate that argument based reasoning as characterised by ASPIC+ is - according to the axioms of [9] - non-cumulative and non-monotonic, and therefore weaker than the weakest non-monotonic reasoning systems they considered possible. This weakness underpins ASPIC+'s success in modelling other reasoning systems, and we conclude by considering the relationship between ASPIC+ and other weak logical systems.

Chatschik Bisdikian, Federico Cerutti, Yuqing Tang et al.

In this paper we describe a decision process framework allowing an agent to decide what information it should reveal to its neighbours within a communication graph in order to maximise its utility. We assume that these neighbours can pass information onto others within the graph. The inferences made by agents receiving the messages can have a positive or negative impact on the information providing agent, and our decision process seeks to identify how a message should be modified in order to be most beneficial to the information producer. Our decision process is based on the provider's subjective beliefs about others in the system, and therefore makes extensive use of the notion of trust. Our core contributions are therefore the construction of a model of information propagation; the description of the agent's decision procedure; and an analysis of some of its properties.

Federico Cerutti, Alice Toniolo, Nir Oren et al.

Computational trust mechanisms aim to produce trust ratings from both direct and indirect information about agents' behaviour. Subjective Logic (SL) has been widely adopted as the core of such systems via its fusion and discount operators. In recent research we revisited the semantics of these operators to explore an alternative, geometric interpretation. In this paper we present a principled desiderata for discounting and fusion operators in SL. Building upon this we present operators that satisfy these desirable properties, including a family of discount operators. We then show, through a rigorous empirical study, that specific, geometrically interpreted operators significantly outperform standard SL operators in estimating ground truth. These novel operators offer real advantages for computational models of trust and reputation, in which they may be employed without modifying other aspects of an existing system.