Pub Date : 2025-04-17DOI: 10.1016/j.artint.2025.104334
Francesco Bacchiocchi, Matteo Castiglioni, Nicola Gatti, Alberto Marchesi
We study principal-agent problems in which a principal commits to an outcome-dependent payment scheme—called contract—in order to induce an agent to take a costly, unobservable action leading to favorable outcomes. We consider a generalization of the classical (single-round) version of the problem in which the principal interacts with the agent by committing to contracts over multiple rounds. The principal has no information about the agent, and they have to learn an optimal contract by only observing the outcome realized at each round. We focus on settings in which the size of the agent's action space is small. We design an algorithm that learns an approximately-optimal contract with high probability in a number of rounds polynomial in the size of the outcome space, when the number of actions is constant. Our algorithm solves an open problem by Zhu et al. [1]. Moreover, it can also be employed to provide a regret bound in the related online learning setting in which the principal aims at maximizing their cumulative utility over rounds, considerably improving previously-known regret bounds.
{"title":"Learning optimal contracts with small action spaces","authors":"Francesco Bacchiocchi, Matteo Castiglioni, Nicola Gatti, Alberto Marchesi","doi":"10.1016/j.artint.2025.104334","DOIUrl":"10.1016/j.artint.2025.104334","url":null,"abstract":"<div><div>We study <em>principal-agent problems</em> in which a principal commits to an outcome-dependent payment scheme—called <em>contract</em>—in order to induce an agent to take a costly, unobservable action leading to favorable outcomes. We consider a generalization of the classical (single-round) version of the problem in which the principal interacts with the agent by committing to contracts over multiple rounds. The principal has no information about the agent, and they have to learn an optimal contract by only observing the outcome realized at each round. We focus on settings in which the <em>size of the agent's action space is small</em>. We design an algorithm that learns an approximately-optimal contract with high probability in a number of rounds polynomial in the size of the outcome space, when the number of actions is constant. Our algorithm solves an open problem by Zhu et al. <span><span>[1]</span></span>. Moreover, it can also be employed to provide a <span><math><mover><mrow><mi>O</mi></mrow><mrow><mo>˜</mo></mrow></mover><mo>(</mo><msup><mrow><mi>T</mi></mrow><mrow><mn>4</mn><mo>/</mo><mn>5</mn></mrow></msup><mo>)</mo></math></span> regret bound in the related online learning setting in which the principal aims at maximizing their cumulative utility over rounds, considerably improving previously-known regret bounds.</div></div>","PeriodicalId":8434,"journal":{"name":"Artificial Intelligence","volume":"344 ","pages":"Article 104334"},"PeriodicalIF":5.1,"publicationDate":"2025-04-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143859966","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-04-16DOI: 10.1016/j.artint.2025.104335
Xiaohui Bei , Biaoshuai Tao , Jiajun Wu , Mingwei Yang
We study the problem of allocating divisible resources among n agents, hopefully in a fair and efficient manner. With the presence of strategic agents, additional incentive guarantees are also necessary, and the problem of designing fair and efficient mechanisms becomes much less tractable. While there are flourishing positive results against strategic agents for homogeneous divisible items, very few of them are known to hold in cake cutting.
We show that the Maximum Nash Welfare (MNW) mechanism, which provides desirable fairness and efficiency guarantees and achieves an incentive ratio of 2 for homogeneous divisible items, also has an incentive ratio of 2 in cake cutting. Remarkably, this result holds even without the free disposal assumption, which is hard to get rid of in the design of truthful cake cutting mechanisms.
Moreover, we show that, for cake cutting, the Partial Allocation (PA) mechanism proposed by Cole et al. [1], which is truthful and -MNW for homogeneous divisible items, has an incentive ratio between and when randomization is allowed, can be turned to be truthful in expectation. Given two alternatives for a trade-off between incentive ratio and Nash welfare provided by the MNW and PA mechanisms, we establish an interpolation between them for both cake cutting and homogeneous divisible items.
Finally, we study the optimal incentive ratio achievable by envy-free cake cutting mechanisms. We first give an envy-free mechanism for two agents with an incentive ratio of 4/3. Then, we show that any envy-free cake cutting mechanism with the connected pieces constraint has an incentive ratio of .
{"title":"The incentive guarantees behind Nash welfare in divisible resources allocation","authors":"Xiaohui Bei , Biaoshuai Tao , Jiajun Wu , Mingwei Yang","doi":"10.1016/j.artint.2025.104335","DOIUrl":"10.1016/j.artint.2025.104335","url":null,"abstract":"<div><div>We study the problem of allocating divisible resources among <em>n</em> agents, hopefully in a fair and efficient manner. With the presence of strategic agents, additional incentive guarantees are also necessary, and the problem of designing fair and efficient mechanisms becomes much less tractable. While there are flourishing positive results against strategic agents for homogeneous divisible items, very few of them are known to hold in cake cutting.</div><div>We show that the Maximum Nash Welfare (MNW) mechanism, which provides desirable fairness and efficiency guarantees and achieves an <em>incentive ratio</em> of 2 for homogeneous divisible items, also has an incentive ratio of 2 in cake cutting. Remarkably, this result holds even without the free disposal assumption, which is hard to get rid of in the design of truthful cake cutting mechanisms.</div><div>Moreover, we show that, for cake cutting, the Partial Allocation (PA) mechanism proposed by Cole et al. <span><span>[1]</span></span>, which is truthful and <span><math><mn>1</mn><mo>/</mo><mi>e</mi></math></span>-MNW for homogeneous divisible items, has an incentive ratio between <span><math><mo>[</mo><msup><mrow><mi>e</mi></mrow><mrow><mn>1</mn><mo>/</mo><mi>e</mi></mrow></msup><mo>,</mo><mi>e</mi><mo>]</mo></math></span> and when randomization is allowed, can be turned to be truthful in expectation. Given two alternatives for a trade-off between incentive ratio and Nash welfare provided by the MNW and PA mechanisms, we establish an interpolation between them for both cake cutting and homogeneous divisible items.</div><div>Finally, we study the optimal incentive ratio achievable by envy-free cake cutting mechanisms. We first give an envy-free mechanism for two agents with an incentive ratio of 4/3. Then, we show that any envy-free cake cutting mechanism with the connected pieces constraint has an incentive ratio of <span><math><mi>Θ</mi><mo>(</mo><mi>n</mi><mo>)</mo></math></span>.</div></div>","PeriodicalId":8434,"journal":{"name":"Artificial Intelligence","volume":"344 ","pages":"Article 104335"},"PeriodicalIF":5.1,"publicationDate":"2025-04-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143856006","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-03-28DOI: 10.1016/j.artint.2025.104332
Stanisław Szufa , Niclas Boehmer , Robert Bredereck , Piotr Faliszewski , Rolf Niedermeier , Piotr Skowron , Arkadii Slinko , Nimrod Talmon
Our main contribution is the introduction of the map of elections framework. A map of elections consists of three main elements: (1) a dataset of elections (i.e., collections of ordinal votes over given sets of candidates), (2) a way of measuring similarities between these elections, and (3) a representation of the elections in the 2D Euclidean space as points, so that the more similar two elections are, the closer are their points. In our maps, we mostly focus on datasets of synthetic elections, but we also show an example of a map over real-life ones. To measure similarities, we would have preferred to use, e.g., the isomorphic swap distance, but this is infeasible due to its high computational complexity. Hence, we propose polynomial-time computable positionwise distance and use it instead. Regarding the representations in 2D Euclidean space, we mostly use the Kamada-Kawai algorithm, but we also show two alternatives. We develop the necessary theoretical results to form our maps and argue experimentally that they are accurate and credible. Further, we show how coloring the elections in a map according to various criteria helps in analyzing results of a number of experiments. In particular, we show colorings according to the scores of winning candidates or committees, running times of ILP-based winner determination algorithms, and approximation ratios achieved by particular algorithms.
{"title":"Drawing a map of elections","authors":"Stanisław Szufa , Niclas Boehmer , Robert Bredereck , Piotr Faliszewski , Rolf Niedermeier , Piotr Skowron , Arkadii Slinko , Nimrod Talmon","doi":"10.1016/j.artint.2025.104332","DOIUrl":"10.1016/j.artint.2025.104332","url":null,"abstract":"<div><div>Our main contribution is the introduction of the map of elections framework. A map of elections consists of three main elements: (1) a dataset of elections (i.e., collections of ordinal votes over given sets of candidates), (2) a way of measuring similarities between these elections, and (3) a representation of the elections in the 2D Euclidean space as points, so that the more similar two elections are, the closer are their points. In our maps, we mostly focus on datasets of synthetic elections, but we also show an example of a map over real-life ones. To measure similarities, we would have preferred to use, e.g., the isomorphic swap distance, but this is infeasible due to its high computational complexity. Hence, we propose polynomial-time computable positionwise distance and use it instead. Regarding the representations in 2D Euclidean space, we mostly use the Kamada-Kawai algorithm, but we also show two alternatives. We develop the necessary theoretical results to form our maps and argue experimentally that they are accurate and credible. Further, we show how coloring the elections in a map according to various criteria helps in analyzing results of a number of experiments. In particular, we show colorings according to the scores of winning candidates or committees, running times of ILP-based winner determination algorithms, and approximation ratios achieved by particular algorithms.</div></div>","PeriodicalId":8434,"journal":{"name":"Artificial Intelligence","volume":"343 ","pages":"Article 104332"},"PeriodicalIF":5.1,"publicationDate":"2025-03-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143767706","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Recently, we are witnessing an increase in computation power and memory, leading to strong AI algorithms becoming applicable in areas affecting our daily lives. We focus on AI planning solutions for complex, real-life decision-making problems under uncertainty, such as autonomous driving. Human trust in such AI-based systems is essential for their acceptance and market penetration. Moreover, users need to establish appropriate levels of trust to benefit the most from these systems. Previous studies have motivated this work, showing that users can benefit from receiving (handcrafted) information about the reasoning of a stochastic AI planner, for example, controlling automated driving maneuvers. Our solution to automating these hand-crafted notifications with explainable AI algorithms, XAI, includes studying: (1) what explanations can be generated from an AI planning system, applied to a real-world problem, in real-time? What is that content that can be processed from a planner's reasoning that can help users understand and trust the system controlling a behavior they are experiencing? (2) when can this information be displayed? and (3) how shall we display this information to an end user? The value of these computed XAI notifications has been assessed through an online user study with 800 participants, experiencing simulated automated driving scenarios. Our results show that real time XAI notifications decrease significantly subjective misunderstanding of participants compared to those that received only a dynamic HMI display. Also, our XAI solution significantly increases the level of understanding of participants with prior ADAS experience and of participants that lack such experience but have non-negative prior trust to ADAS features. The level of trust significantly increases when XAI was provided to a more restricted set of the participants, including those over 60 years old, with prior ADAS experience and non-negative prior trust attitude to automated features.
{"title":"The value of real-time automated explanations in stochastic planning","authors":"Claudia V. Goldman , Ronit Bustin , Wenyuan Qi , Zhengyu Xing , Rachel McPhearson-White , Sally Rogers","doi":"10.1016/j.artint.2025.104323","DOIUrl":"10.1016/j.artint.2025.104323","url":null,"abstract":"<div><div>Recently, we are witnessing an increase in computation power and memory, leading to strong AI algorithms becoming applicable in areas affecting our daily lives. We focus on AI planning solutions for complex, real-life decision-making problems under uncertainty, such as autonomous driving. Human trust in such AI-based systems is essential for their acceptance and market penetration. Moreover, users need to establish appropriate levels of trust to benefit the most from these systems. Previous studies have motivated this work, showing that users can benefit from receiving (handcrafted) information about the reasoning of a stochastic AI planner, for example, controlling automated driving maneuvers. Our solution to automating these hand-crafted notifications with explainable AI algorithms, XAI, includes studying: (1) what explanations can be generated from an AI planning system, applied to a real-world problem, in real-time? What is that content that can be processed from a planner's reasoning that can help users understand and trust the system controlling a behavior they are experiencing? (2) when can this information be displayed? and (3) how shall we display this information to an end user? The value of these computed XAI notifications has been assessed through an online user study with 800 participants, experiencing simulated automated driving scenarios. Our results show that real time XAI notifications decrease significantly subjective misunderstanding of participants compared to those that received only a dynamic HMI display. Also, our XAI solution significantly increases the level of understanding of participants with prior ADAS experience and of participants that lack such experience but have non-negative prior trust to ADAS features. The level of trust significantly increases when XAI was provided to a more restricted set of the participants, including those over 60 years old, with prior ADAS experience and non-negative prior trust attitude to automated features.</div></div>","PeriodicalId":8434,"journal":{"name":"Artificial Intelligence","volume":"343 ","pages":"Article 104323"},"PeriodicalIF":5.1,"publicationDate":"2025-03-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143815962","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-03-07DOI: 10.1016/j.artint.2025.104322
Stephen Kobourov , Maarten Löffler , Fabrizio Montecchiani , Marcin Pilipczuk , Ignaz Rutter , Raimund Seidel , Manuel Sorge , Jules Wulms
A decision tree recursively splits a feature space and then assigns class labels based on the resulting partition. Decision trees have been part of the basic machine-learning toolkit for decades. A large body of work considers heuristic algorithms that compute a decision tree from training data, usually aiming to minimize in particular the size of the resulting tree. In contrast, little is known about the complexity of the underlying computational problem of computing a minimum-size tree for the given training data. We study this problem with respect to the number d of dimensions of the feature space , which contains n training examples. We show that it can be solved in time, but under reasonable complexity-theoretic assumptions it is not possible to achieve running time. The problem is solvable in time if there are exactly two classes and R is an upper bound on the number of tree leaves labeled with the first class.
{"title":"The influence of dimensions on the complexity of computing decision trees","authors":"Stephen Kobourov , Maarten Löffler , Fabrizio Montecchiani , Marcin Pilipczuk , Ignaz Rutter , Raimund Seidel , Manuel Sorge , Jules Wulms","doi":"10.1016/j.artint.2025.104322","DOIUrl":"10.1016/j.artint.2025.104322","url":null,"abstract":"<div><div>A decision tree recursively splits a feature space <span><math><msup><mrow><mi>R</mi></mrow><mrow><mi>d</mi></mrow></msup></math></span> and then assigns class labels based on the resulting partition. Decision trees have been part of the basic machine-learning toolkit for decades. A large body of work considers heuristic algorithms that compute a decision tree from training data, usually aiming to minimize in particular the size of the resulting tree. In contrast, little is known about the complexity of the underlying computational problem of computing a minimum-size tree for the given training data. We study this problem with respect to the number <em>d</em> of dimensions of the feature space <span><math><msup><mrow><mi>R</mi></mrow><mrow><mi>d</mi></mrow></msup></math></span>, which contains <em>n</em> training examples. We show that it can be solved in <span><math><mi>O</mi><mo>(</mo><msup><mrow><mi>n</mi></mrow><mrow><mn>2</mn><mi>d</mi><mo>+</mo><mn>1</mn></mrow></msup><mo>)</mo></math></span> time, but under reasonable complexity-theoretic assumptions it is not possible to achieve <span><math><mi>f</mi><mo>(</mo><mi>d</mi><mo>)</mo><mo>⋅</mo><msup><mrow><mi>n</mi></mrow><mrow><mi>o</mi><mo>(</mo><mi>d</mi><mo>/</mo><mi>log</mi><mo></mo><mi>d</mi><mo>)</mo></mrow></msup></math></span> running time. The problem is solvable in <span><math><msup><mrow><mo>(</mo><mi>d</mi><mi>R</mi><mo>)</mo></mrow><mrow><mi>O</mi><mo>(</mo><mi>d</mi><mi>R</mi><mo>)</mo></mrow></msup><mo>⋅</mo><msup><mrow><mi>n</mi></mrow><mrow><mn>1</mn><mo>+</mo><mi>o</mi><mo>(</mo><mn>1</mn><mo>)</mo></mrow></msup></math></span> time if there are exactly two classes and <em>R</em> is an upper bound on the number of tree leaves labeled with the first class.</div></div>","PeriodicalId":8434,"journal":{"name":"Artificial Intelligence","volume":"343 ","pages":"Article 104322"},"PeriodicalIF":5.1,"publicationDate":"2025-03-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143580179","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-03-03DOI: 10.1016/j.artint.2025.104311
Matti Järvisalo , Tuomo Lehtonen , Andreas Niskanen
The study of computational models of argumentation and the development of practical automated approaches to reasoning over the models has developed into a vibrant area of artificial intelligence research in recent years. The series of International Competitions on Computational Models of Argumentation (ICCMA) aims at nurturing research and development of practical reasoning algorithms for models of argumentation. Organized biennially, the ICCMA competitions provide a snapshot of the current state of the art in algorithm implementations for central fundamental reasoning tasks over models of argumentation. The year 2023 marked the 5th instantiation of International Competitions on Computational Models of Argumentation, ICCMA 2023. We provide a comprehensive overview of ICCMA 2023, including details on the various new developments introduced in 2023, overview of the participating solvers, extensive details on the competition benchmarks and results, as well as lessons learned.
{"title":"ICCMA 2023: 5th International Competition on Computational Models of Argumentation","authors":"Matti Järvisalo , Tuomo Lehtonen , Andreas Niskanen","doi":"10.1016/j.artint.2025.104311","DOIUrl":"10.1016/j.artint.2025.104311","url":null,"abstract":"<div><div>The study of computational models of argumentation and the development of practical automated approaches to reasoning over the models has developed into a vibrant area of artificial intelligence research in recent years. The series of International Competitions on Computational Models of Argumentation (ICCMA) aims at nurturing research and development of practical reasoning algorithms for models of argumentation. Organized biennially, the ICCMA competitions provide a snapshot of the current state of the art in algorithm implementations for central fundamental reasoning tasks over models of argumentation. The year 2023 marked the 5th instantiation of International Competitions on Computational Models of Argumentation, ICCMA 2023. We provide a comprehensive overview of ICCMA 2023, including details on the various new developments introduced in 2023, overview of the participating solvers, extensive details on the competition benchmarks and results, as well as lessons learned.</div></div>","PeriodicalId":8434,"journal":{"name":"Artificial Intelligence","volume":"342 ","pages":"Article 104311"},"PeriodicalIF":5.1,"publicationDate":"2025-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143582668","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Weighted First Order Model Counting (WFOMC) is fundamental to probabilistic inference in statistical relational learning models. As WFOMC is known to be intractable in general (#P-complete), logical fragments that admit polynomial time WFOMC are of significant interest. Such fragments are called domain liftable. Recent works have shown that the two-variable fragment of first order logic extended with counting quantifiers (C2) is domain-liftable. However, many properties of real-world data, like acyclicity in citation networks and connectivity in social networks, cannot be modeled in C2, or first order logic in general. In this work, we expand the domain liftability of C2 with multiple such properties. We show that any C2 sentence remains domain liftable when one of its relations is restricted to represent a directed acyclic graph, a connected graph, a tree (resp. a directed tree) or a forest (resp. a directed forest). All our results rely on a novel and general methodology of counting by splitting. Besides their application to probabilistic inference, our results provide a general framework for counting combinatorial structures. We expand a vast array of previous results in discrete mathematics literature on directed acyclic graphs, phylogenetic networks, etc.
{"title":"Lifted inference beyond first-order logic","authors":"Sagar Malhotra , Davide Bizzaro , Luciano Serafini","doi":"10.1016/j.artint.2025.104310","DOIUrl":"10.1016/j.artint.2025.104310","url":null,"abstract":"<div><div>Weighted First Order Model Counting (WFOMC) is fundamental to probabilistic inference in statistical relational learning models. As WFOMC is known to be intractable in general (#P-complete), logical fragments that admit polynomial time WFOMC are of significant interest. Such fragments are called <em>domain liftable</em>. Recent works have shown that the two-variable fragment of first order logic extended with counting quantifiers (C<sup>2</sup>) is domain-liftable. However, many properties of real-world data, like <em>acyclicity</em> in citation networks and <em>connectivity</em> in social networks, cannot be modeled in C<sup>2</sup>, or first order logic in general. In this work, we expand the domain liftability of C<sup>2</sup> with multiple such properties. We show that any C<sup>2</sup> sentence remains domain liftable when one of its relations is restricted to represent a directed acyclic graph, a connected graph, a tree (resp. a directed tree) or a forest (resp. a directed forest). All our results rely on a novel and general methodology of <em>counting by splitting</em>. Besides their application to probabilistic inference, our results provide a general framework for counting combinatorial structures. We expand a vast array of previous results in discrete mathematics literature on directed acyclic graphs, phylogenetic networks, etc.</div></div>","PeriodicalId":8434,"journal":{"name":"Artificial Intelligence","volume":"342 ","pages":"Article 104310"},"PeriodicalIF":5.1,"publicationDate":"2025-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143479252","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-02-22DOI: 10.1016/j.artint.2025.104309
Christopher D. Wirz , Julie L. Demuth , Ann Bostrom , Mariana G. Cains , Imme Ebert-Uphoff , David John Gagne II , Andrea Schumacher , Amy McGovern , Deianna Madlambayan
Developers and academics have grown increasingly interested in developing “trustworthy” artificial intelligence (AI). However, this aim is difficult to achieve in practice, especially given trust and trustworthiness are complex, multifaceted concepts that cannot be completely guaranteed nor built entirely into an AI system. We have drawn on the breadth of trust-related literature across multiple disciplines and fields to synthesize knowledge pertaining to interpersonal trust, trust in automation, and risk and trust. Based on this review we have (re)conceptualized trustworthiness in practice as being both (a) perceptual, meaning that a user assesses whether, when, and to what extent AI model output is trustworthy, even if it has been developed in adherence to AI trustworthiness standards, and (b) context-dependent, meaning that a user's perceived trustworthiness and use of an AI model can vary based on the specifics of their situation (e.g., time-pressures for decision-making, high-stakes decisions). We provide our reconceptualization to nuance how trustworthiness is thought about, studied, and evaluated by the AI community in ways that are more aligned with past theoretical research.
{"title":"(Re)Conceptualizing trustworthy AI: A foundation for change","authors":"Christopher D. Wirz , Julie L. Demuth , Ann Bostrom , Mariana G. Cains , Imme Ebert-Uphoff , David John Gagne II , Andrea Schumacher , Amy McGovern , Deianna Madlambayan","doi":"10.1016/j.artint.2025.104309","DOIUrl":"10.1016/j.artint.2025.104309","url":null,"abstract":"<div><div>Developers and academics have grown increasingly interested in developing “trustworthy” artificial intelligence (AI). However, this aim is difficult to achieve in practice, especially given trust and trustworthiness are complex, multifaceted concepts that cannot be completely guaranteed nor built entirely into an AI system. We have drawn on the breadth of trust-related literature across multiple disciplines and fields to synthesize knowledge pertaining to interpersonal trust, trust in automation, and risk and trust. Based on this review we have (re)conceptualized trustworthiness in practice as being both (a) perceptual, meaning that a user assesses whether, when, and to what extent AI model output is trustworthy, even if it has been developed in adherence to AI trustworthiness standards, and (b) context-dependent, meaning that a user's perceived trustworthiness and use of an AI model can vary based on the specifics of their situation (e.g., time-pressures for decision-making, high-stakes decisions). We provide our reconceptualization to nuance how trustworthiness is thought about, studied, and evaluated by the AI community in ways that are more aligned with past theoretical research.</div></div>","PeriodicalId":8434,"journal":{"name":"Artificial Intelligence","volume":"342 ","pages":"Article 104309"},"PeriodicalIF":5.1,"publicationDate":"2025-02-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143511262","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-02-13DOI: 10.1016/j.artint.2025.104308
Chao Bian , Yawen Zhou , Miqing Li , Chao Qian
Evolutionary algorithms (EAs) have been widely and successfully applied to solve multi-objective optimization problems, due to their nature of population-based search. Population update, a key component in multi-objective EAs (MOEAs), is usually performed in a greedy, deterministic manner. That is, the next-generation population is formed by selecting the best solutions from the current population and newly-generated solutions (irrespective of the selection criteria used such as Pareto dominance, crowdedness and indicators). In this paper, we analytically present that stochastic population update can be beneficial for the search of MOEAs. Specifically, we prove that the expected running time of two well-established MOEAs, SMS-EMOA and NSGA-II, for solving two bi-objective problems, OneJumpZeroJump and bi-objective RealRoyalRoad, can be exponentially decreased if replacing its deterministic population update mechanism by a stochastic one. Empirical studies also verify the effectiveness of the proposed population update method. This work is an attempt to show the benefit of introducing randomness into the population update of MOEAs. Its positive results, which might hold more generally, should encourage the exploration of developing new MOEAs in the area.
{"title":"Stochastic population update can provably be helpful in multi-objective evolutionary algorithms","authors":"Chao Bian , Yawen Zhou , Miqing Li , Chao Qian","doi":"10.1016/j.artint.2025.104308","DOIUrl":"10.1016/j.artint.2025.104308","url":null,"abstract":"<div><div>Evolutionary algorithms (EAs) have been widely and successfully applied to solve multi-objective optimization problems, due to their nature of population-based search. Population update, a key component in multi-objective EAs (MOEAs), is usually performed in a greedy, deterministic manner. That is, the next-generation population is formed by selecting the best solutions from the current population and newly-generated solutions (irrespective of the selection criteria used such as Pareto dominance, crowdedness and indicators). In this paper, we analytically present that stochastic population update can be beneficial for the search of MOEAs. Specifically, we prove that the expected running time of two well-established MOEAs, SMS-EMOA and NSGA-II, for solving two bi-objective problems, OneJumpZeroJump and bi-objective RealRoyalRoad, can be exponentially decreased if replacing its deterministic population update mechanism by a stochastic one. Empirical studies also verify the effectiveness of the proposed population update method. This work is an attempt to show the benefit of introducing randomness into the population update of MOEAs. Its positive results, which might hold more generally, should encourage the exploration of developing new MOEAs in the area.</div></div>","PeriodicalId":8434,"journal":{"name":"Artificial Intelligence","volume":"341 ","pages":"Article 104308"},"PeriodicalIF":5.1,"publicationDate":"2025-02-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143430306","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-02-13DOI: 10.1016/j.artint.2025.104307
Alejandra López de Aberasturi Gómez, Carles Sierra, Jordi Sabater-Mir
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.
{"title":"Grounded predictions of teamwork as a one-shot game: A multiagent multi-armed bandits approach","authors":"Alejandra López de Aberasturi Gómez, Carles Sierra, Jordi Sabater-Mir","doi":"10.1016/j.artint.2025.104307","DOIUrl":"10.1016/j.artint.2025.104307","url":null,"abstract":"<div><div>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.</div></div>","PeriodicalId":8434,"journal":{"name":"Artificial Intelligence","volume":"341 ","pages":"Article 104307"},"PeriodicalIF":5.1,"publicationDate":"2025-02-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143422377","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
扫码关注我们
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号