Artificial Intelligence最新文献_第6页

On the disjunctive rational closure of a conditional knowledge base 论条件知识库的析取理性闭包

IF 4.6 2区计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Artificial Intelligence

Pub Date : 2025-11-01 Epub Date: 2025-09-12 DOI: 10.1016/j.artint.2025.104418

Richard Booth , Ivan Varzinczak

One of the most widely investigated decision problems in symbolic AI is that of which conditional sentences of the form “if α, then normally β” should follow from a knowledge base containing this type of statements. Probably, the most notable approach to this problem is the rational closure construction put forward by Lehmann and Magidor in the'90s, which has been adapted to logical languages of various expressive powers since then. At the core of rational closure is the Rational Monotonicity property, which allows one to retain existing (defeasible) conclusions whenever new information cannot be negated by existing conclusions. As it turns out, Rational Monotonicity is not universally accepted, with many researchers advocating the investigation of weaker versions thereof leading to a larger class of consequence relations. A case in point is that of the Disjunctive Rationality property, which states that if one may draw a (defeasible) conclusion from a disjunction of premises, then one should be able to draw this conclusion from at least one of the premises taken alone. While there are convincing arguments that the rational closure forms the ‘simplest’ rational consequence relation extending a given set of conditionals, the question of what the simplest disjunctive consequence relation in this setting is has not been explored in depth. In this article, we do precisely that by motivating and proposing a concrete construction of the disjunctive rational closure of a conditional knowledge base, of which the properties and consequences of its adoption we also investigate in detail. (Previous versions of this work have been selected for presentation at the 18th International Workshop on Nonmonotonic Reasoning (NMR 2020) [1] and at the 35th AAAI Conference on Artificial Intelligence (AAAI 2021) [2]. The present submission extends and elaborates on both papers.)

符号人工智能中最广泛研究的决策问题之一是“如果α，则通常β”形式的条件句应该从包含此类语句的知识库中跟随。对于这个问题，最值得注意的方法可能是莱曼和马吉多尔在90年代提出的理性闭包结构，从那时起，它就被适应于各种表达能力的逻辑语言。有理闭包的核心是有理单调性属性，它允许在现有结论不能否定新信息时保留现有的（可废止的）结论。事实证明，理性单调性并没有被普遍接受，许多研究人员提倡对其较弱版本的研究，从而导致更大的结果关系类别。一个恰当的例子是析取理性属性，它指出，如果一个人可以从前提的析取中得出（可推翻的）结论，那么他应该能够从至少一个单独的前提中得出这个结论。虽然有令人信服的论点认为，有理闭包形成了扩展给定条件集的“最简单”的理性推论关系，但在这种情况下，最简单的析取推论关系是什么这个问题还没有深入探讨。在本文中，我们正是通过激励和提出条件知识库的析取理性闭包的具体结构来做到这一点，我们还详细研究了其采用的性质和后果。(这项工作的先前版本已被选中在第18届非单调推理国际研讨会（NMR 2020）[1]和第35届AAAI人工智能会议（AAAI 2021）[2]上发表。本报告对这两篇论文进行了扩展和阐述。)

{"title":"On the disjunctive rational closure of a conditional knowledge base","authors":"Richard Booth , Ivan Varzinczak","doi":"10.1016/j.artint.2025.104418","DOIUrl":"10.1016/j.artint.2025.104418","url":null,"abstract":"<div><div>One of the most widely investigated decision problems in symbolic AI is that of which conditional sentences of the form “if <em>α</em>, then normally <em>β</em>” should follow from a knowledge base containing this type of statements. Probably, the most notable approach to this problem is the rational closure construction put forward by Lehmann and Magidor in the'90s, which has been adapted to logical languages of various expressive powers since then. At the core of rational closure is the Rational Monotonicity property, which allows one to retain existing (defeasible) conclusions whenever new information cannot be negated by existing conclusions. As it turns out, Rational Monotonicity is not universally accepted, with many researchers advocating the investigation of weaker versions thereof leading to a larger class of consequence relations. A case in point is that of the Disjunctive Rationality property, which states that if one may draw a (defeasible) conclusion from a disjunction of premises, then one should be able to draw this conclusion from at least one of the premises taken alone. While there are convincing arguments that the rational closure forms the ‘simplest’ rational consequence relation extending a given set of conditionals, the question of what the simplest disjunctive consequence relation in this setting is has not been explored in depth. In this article, we do precisely that by motivating and proposing a concrete construction of the disjunctive rational closure of a conditional knowledge base, of which the properties and consequences of its adoption we also investigate in detail. (Previous versions of this work have been selected for presentation at the 18th International Workshop on Nonmonotonic Reasoning (NMR 2020) <span><span>[1]</span></span> and at the 35th AAAI Conference on Artificial Intelligence (AAAI 2021) <span><span>[2]</span></span>. The present submission extends and elaborates on both papers.)</div></div>","PeriodicalId":8434,"journal":{"name":"Artificial Intelligence","volume":"348 ","pages":"Article 104418"},"PeriodicalIF":4.6,"publicationDate":"2025-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145094874","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}

引用次数: 0

BATED: Learning fair representation for Pre-trained Language Models via biased teacher-guided disentanglement BATED：通过有偏见的教师引导的解纠缠来学习预训练语言模型的公平表示

IF 4.6 2区计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Artificial Intelligence

Pub Date : 2025-11-01 Epub Date: 2025-08-08 DOI: 10.1016/j.artint.2025.104401

Yingji Li , Mengnan Du , Rui Song , Mu Liu , Ying Wang

With the rapid development of Pre-trained Language Models (PLMs) and their widespread deployment in various real-world applications, social biases of PLMs have attracted increasing attention, especially the fairness of downstream tasks, which potentially affects the development and stability of society. Among existing debiasing methods, intrinsic debiasing methods are not necessarily effective when applied to downstream tasks, and the downstream fine-tuning process may introduce new biases or catastrophic forgetting. Most extrinsic debiasing methods rely on sensitive attribute words as prior knowledge to supervise debiasing training. However, it is difficult to collect sensitive attribute information of real data due to privacy and regulation. Moreover, limited sensitive attribute words may lead to inadequate debiasing training. To this end, this paper proposes a debiasing method to learn fair representation for PLMs via BiAsed TEacher-guided Disentanglement (called BATED). Specific to downstream tasks, BATED performs debiasing training under the guidance of a biased teacher model rather than relying on sensitive attribute information of the training data. First, we leverage causal contrastive learning to train a task-agnostic general biased teacher model. We then employ Variational Auto-Encoder (VAE) to disentangle the PLM-encoded representation into the fair representation and the biased representation. The Biased representation is further decoupled via biased teacher-guided disentanglement, while the fair representation learn downstream tasks. Therefore, BATED guarantees the performance of downstream tasks while improving the fairness. Experimental results on seven PLMs testing three downstream tasks demonstrate that BATED outperforms the state-of-the-art overall in terms of fairness and performance on downstream tasks.

随着预训练语言模型（Pre-trained Language Models, PLMs）的快速发展和在各种现实应用中的广泛应用，PLMs的社会偏见越来越受到人们的关注，尤其是下游任务的公平性问题，它可能会影响社会的发展和稳定。在现有的去偏方法中，内在去偏方法在应用于下游任务时不一定有效，下游微调过程可能会引入新的偏差或灾难性遗忘。大多数外在去偏方法依赖敏感属性词作为先验知识来监督去偏训练。然而，由于隐私和监管的原因，难以收集到真实数据的敏感属性信息。此外，有限的敏感属性词可能导致去偏训练不足。为此，本文提出了一种通过有偏见的教师引导的解纠缠（BATED）来学习plm公平表示的去偏见方法。针对下游任务，BATED在偏向教师模型的指导下进行去偏向训练，而不是依赖于训练数据的敏感属性信息。首先，我们利用因果对比学习来训练一个任务不可知论的一般偏见教师模型。然后，我们使用变分自编码器（VAE）将plm编码表示分解为公平表示和偏见表示。有偏见的表示通过有偏见的教师引导的解纠缠进一步解耦，而公平表示学习下游任务。因此，BATED在保证下游任务性能的同时，提高了公平性。在七个plm测试三个下游任务的实验结果表明，BATED在下游任务的公平性和性能方面总体上优于最先进的技术。

{"title":"BATED: Learning fair representation for Pre-trained Language Models via biased teacher-guided disentanglement","authors":"Yingji Li , Mengnan Du , Rui Song , Mu Liu , Ying Wang","doi":"10.1016/j.artint.2025.104401","DOIUrl":"10.1016/j.artint.2025.104401","url":null,"abstract":"<div><div>With the rapid development of Pre-trained Language Models (PLMs) and their widespread deployment in various real-world applications, social biases of PLMs have attracted increasing attention, especially the fairness of downstream tasks, which potentially affects the development and stability of society. Among existing debiasing methods, intrinsic debiasing methods are not necessarily effective when applied to downstream tasks, and the downstream fine-tuning process may introduce new biases or catastrophic forgetting. Most extrinsic debiasing methods rely on sensitive attribute words as prior knowledge to supervise debiasing training. However, it is difficult to collect sensitive attribute information of real data due to privacy and regulation. Moreover, limited sensitive attribute words may lead to inadequate debiasing training. To this end, this paper proposes a debiasing method to learn fair representation for PLMs via <strong>B</strong>i<strong>A</strong>sed <strong>TE</strong>acher-guided <strong>D</strong>isentanglement (called <strong>BATED</strong>). Specific to downstream tasks, BATED performs debiasing training under the guidance of a biased teacher model rather than relying on sensitive attribute information of the training data. First, we leverage causal contrastive learning to train a task-agnostic general biased teacher model. We then employ Variational Auto-Encoder (VAE) to disentangle the PLM-encoded representation into the fair representation and the biased representation. The Biased representation is further decoupled via biased teacher-guided disentanglement, while the fair representation learn downstream tasks. Therefore, BATED guarantees the performance of downstream tasks while improving the fairness. Experimental results on seven PLMs testing three downstream tasks demonstrate that BATED outperforms the state-of-the-art overall in terms of fairness and performance on downstream tasks.</div></div>","PeriodicalId":8434,"journal":{"name":"Artificial Intelligence","volume":"348 ","pages":"Article 104401"},"PeriodicalIF":4.6,"publicationDate":"2025-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144810517","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}

引用次数: 0

Bridging theory and practice in bidirectional heuristic search with front-to-end consistent heuristics 基于前端一致性启发式的双向启发式搜索理论与实践的桥梁

IF 4.6 2区计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Artificial Intelligence

Pub Date : 2025-11-01 Epub Date: 2025-09-19 DOI: 10.1016/j.artint.2025.104420

Lior Siag, Shahaf S. Shperberg

Recent research on bidirectional heuristic search (BiHS) has been shaped by the must-expand pairs (MEP) theory, which identifies the pairs of nodes that must be expanded to ensure solution optimality. Another line of research has focused on algorithms utilizing lower bounds derived from consistent heuristics during the search. This paper bridges these two approaches, offering a unified framework that demonstrates how both existing and novel algorithms can be derived from MEP theory. We introduce an extended set of bounds, encompassing both previously known and newly formulated ones. Using these bounds, we develop a range of algorithms, each employing different criteria for termination, node selection, and search direction. Finally, we empirically evaluate how these bounds and algorithms impact search efficiency.

双向启发式搜索（BiHS）的最新研究受到必须扩展对（MEP）理论的影响，该理论确定了必须扩展以确保解最优性的节点对。另一项研究集中在利用搜索过程中一致启发式导出的下界的算法上。本文将这两种方法连接起来，提供了一个统一的框架，展示了如何从MEP理论中推导出现有的和新的算法。我们引入一个扩展的界集，包括以前已知的和新制定的。利用这些边界，我们开发了一系列算法，每个算法都采用不同的终止、节点选择和搜索方向标准。最后，我们实证地评估了这些边界和算法如何影响搜索效率。

引用次数: 0

Unsupervised sentence selection for creating a representative corpus in Turkish: An active learning approach 创建土耳其语代表性语料库的无监督句子选择：一种主动学习方法

IF 4.6 2区计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Artificial Intelligence

Pub Date : 2025-11-01 Epub Date: 2025-09-22 DOI: 10.1016/j.artint.2025.104422

Hayri Volkan Agun

In this study, active learning methods adapted for sentence selection of Turkish sentences are evaluated through language learning with neural models. Turkish is an agglutinative language with a complex morphology, where the linguistic properties of words are encoded in suffixes. The active learning methods based on regression, clustering, language models, distance metrics, and neural networks are applied to unlabeled sentence selection. In this respect, a sentence corpus is selected from a larger corpus, with the same number of samples for each target word in intrinsic and extrinsic evaluation tasks. The selected sentences are used for the training of SkipGram, CBOW, and self-attention LSTM language models and extracted embeddings are evaluated by the semantic analogy, POS and sentiment analysis tasks. The evaluation scores of the models trained on the samples selected by the active learning method are compared. The results of the selected sentences based on language models indicate an improvement over random selection based on a static vocabulary. These results also show that the selection affects the quality of unsupervised word embedding extraction even if the target vocabulary is kept the same. Along with the accuracy, the time efficiency of the language models is shown to be better than other methods especially methods based on neural network models, and distance metrics.

在本研究中，通过神经模型的语言学习，评估了适用于土耳其语句子选择的主动学习方法。土耳其语是一种具有复杂形态学的黏合语言，其中单词的语言属性编码在后缀中。将基于回归、聚类、语言模型、距离度量和神经网络的主动学习方法应用于无标记句子的选择。在这方面，从一个更大的语料库中选择一个句子语料库，在内在和外在评价任务中，每个目标词的样本数量相同。选择的句子用于训练SkipGram、CBOW和自关注LSTM语言模型，提取的嵌入通过语义类比、POS和情感分析任务进行评估。比较了采用主动学习方法训练的模型的评价分数。基于语言模型的句子选择结果表明，与基于静态词汇表的随机选择相比，该方法有了改进。这些结果还表明，即使目标词汇保持不变，选择也会影响无监督词嵌入提取的质量。在提高准确率的同时，语言模型的时间效率也优于其他方法，特别是基于神经网络模型和距离度量的方法。

{"title":"Unsupervised sentence selection for creating a representative corpus in Turkish: An active learning approach","authors":"Hayri Volkan Agun","doi":"10.1016/j.artint.2025.104422","DOIUrl":"10.1016/j.artint.2025.104422","url":null,"abstract":"<div><div>In this study, active learning methods adapted for sentence selection of Turkish sentences are evaluated through language learning with neural models. Turkish is an agglutinative language with a complex morphology, where the linguistic properties of words are encoded in suffixes. The active learning methods based on regression, clustering, language models, distance metrics, and neural networks are applied to unlabeled sentence selection. In this respect, a sentence corpus is selected from a larger corpus, with the same number of samples for each target word in intrinsic and extrinsic evaluation tasks. The selected sentences are used for the training of SkipGram, CBOW, and self-attention LSTM language models and extracted embeddings are evaluated by the semantic analogy, POS and sentiment analysis tasks. The evaluation scores of the models trained on the samples selected by the active learning method are compared. The results of the selected sentences based on language models indicate an improvement over random selection based on a static vocabulary. These results also show that the selection affects the quality of unsupervised word embedding extraction even if the target vocabulary is kept the same. Along with the accuracy, the time efficiency of the language models is shown to be better than other methods especially methods based on neural network models, and distance metrics.</div></div>","PeriodicalId":8434,"journal":{"name":"Artificial Intelligence","volume":"348 ","pages":"Article 104422"},"PeriodicalIF":4.6,"publicationDate":"2025-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145104222","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}

引用次数: 0

Centralized training with hybrid execution in multi-agent reinforcement learning via predictive observation imputation 基于预测观测插值的多智能体强化学习集中训练混合执行

IF 4.6 2区计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Artificial Intelligence

Pub Date : 2025-11-01 Epub Date: 2025-09-10 DOI: 10.1016/j.artint.2025.104404

Pedro P. Santos , Diogo S. Carvalho , Miguel Vasco , Alberto Sardinha , Pedro A. Santos , Ana Paiva , Francisco S. Melo

We study hybrid execution in multi-agent reinforcement learning (MARL), a paradigm where agents aim to complete cooperative tasks with arbitrary communication levels at execution time by taking advantage of information-sharing among the agents. Under hybrid execution, the communication level can range from a setting in which no communication is allowed between agents (fully decentralized), to a setting featuring full communication (fully centralized), but the agents do not know beforehand which communication level they will encounter at execution time. We contribute MARO, an approach that makes use of an auto-regressive predictive model, trained in a centralized manner, to estimate missing agents' observations at execution time. We evaluate MARO on standard scenarios and extensions of previous benchmarks tailored to emphasize the impact of partial observability in MARL. Experimental results show that our method consistently outperforms relevant baselines, allowing agents to act with faulty communication while successfully exploiting shared information.

我们研究了多智能体强化学习（MARL）中的混合执行，这是一种智能体旨在利用智能体之间的信息共享来完成在执行时具有任意通信级别的合作任务的范式。在混合执行下，通信级别可以从代理之间不允许通信的设置（完全分散）到具有完全通信的设置（完全集中），但代理事先不知道它们在执行时将遇到哪个通信级别。我们贡献了MARO，一种利用自回归预测模型的方法，以集中的方式训练，来估计缺失代理在执行时的观察值。我们在标准情景和先前基准的扩展中评估MARO，以强调MARL中部分可观测性的影响。实验结果表明，我们的方法始终优于相关基线，允许代理在成功利用共享信息的同时进行错误通信。

{"title":"Centralized training with hybrid execution in multi-agent reinforcement learning via predictive observation imputation","authors":"Pedro P. Santos , Diogo S. Carvalho , Miguel Vasco , Alberto Sardinha , Pedro A. Santos , Ana Paiva , Francisco S. Melo","doi":"10.1016/j.artint.2025.104404","DOIUrl":"10.1016/j.artint.2025.104404","url":null,"abstract":"<div><div>We study <em>hybrid execution</em> in multi-agent reinforcement learning (MARL), a paradigm where agents aim to complete cooperative tasks with arbitrary communication levels at execution time by taking advantage of information-sharing among the agents. Under hybrid execution, the communication level can range from a setting in which no communication is allowed between agents (fully decentralized), to a setting featuring full communication (fully centralized), but the agents do not know beforehand which communication level they will encounter at execution time. We contribute MARO, an approach that makes use of an auto-regressive predictive model, trained in a centralized manner, to estimate missing agents' observations at execution time. We evaluate MARO on standard scenarios and extensions of previous benchmarks tailored to emphasize the impact of partial observability in MARL. Experimental results show that our method consistently outperforms relevant baselines, allowing agents to act with faulty communication while successfully exploiting shared information.</div></div>","PeriodicalId":8434,"journal":{"name":"Artificial Intelligence","volume":"348 ","pages":"Article 104404"},"PeriodicalIF":4.6,"publicationDate":"2025-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145060254","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}

引用次数: 0

Local-MIP: Efficient local search for mixed integer programming local - mip：混合整数规划的高效局部搜索

IF 4.6 2区计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Artificial Intelligence

Pub Date : 2025-11-01 Epub Date: 2025-08-27 DOI: 10.1016/j.artint.2025.104405

Peng Lin , Shaowei Cai , Mengchuan Zou , Jinkun Lin

Mixed Integer Programming (MIP) is a fundamental model in operations research with broad industrial applications. Local search is a powerful methodology for solving complex optimization problems; however, the development of local search algorithms for MIP still needs exploration. In this work, we propose Local-MIP, an efficient local search algorithm tailored for MIP that integrates novel operators and employs a two-mode architecture to adaptively apply operators based on the current solution's feasibility. For the feasible mode, we propose the lift move operator and a corresponding lift process to improve the objective value while maintaining feasibility. For the infeasible mode, we propose the breakthrough move and mixed tight move operators to respectively optimize the objective function and satisfy constraints. To apply operators intelligently, we develop a dynamic weighting scheme that balances the priorities of the objective function and constraints. Furthermore, we propose a two-level scoring function structure that hierarchically selects operations, guiding the search toward high-quality feasible solutions. Experiments are conducted on public benchmarks to compare Local-MIP with state-of-the-art MIP solvers in finding high-quality solutions. The results show that Local-MIP significantly outperforms CPLEX, HiGHS, SCIP, and Feasibility Jump while remaining competitive with the commercial solver Gurobi on challenging problems within short time limits. Moreover, Local-MIP establishes 10 new records on MIPLIB open instances.

混合整数规划（MIP）是运筹学中的一个基本模型，具有广泛的工业应用。局部搜索是解决复杂优化问题的有力方法；然而，MIP局部搜索算法的发展仍有待探索。在这项工作中，我们提出了local -MIP，这是一种为MIP定制的高效本地搜索算法，它集成了新的算子，并采用双模式架构根据当前解决方案的可行性自适应应用算子。对于可行模式，我们提出了升降操作人和相应的升降过程，在保持可行性的同时提高目标值。针对不可行模式，提出了突破移动算子和混合紧密移动算子，分别优化目标函数和满足约束条件。为了智能地应用算子，我们开发了一种动态加权方案来平衡目标函数和约束的优先级。此外，我们提出了一个两级评分函数结构，该结构分层选择操作，指导搜索高质量的可行解决方案。在公共基准上进行实验，以比较Local-MIP与最先进的MIP解决方案在寻找高质量解决方案方面的差异。结果表明，Local-MIP显著优于CPLEX、high、SCIP和可行性跳跃，同时在短时间内与商业求解器Gurobi在具有挑战性的问题上保持竞争力。Local-MIP在MIPLIB开放实例上建立了10条新记录。

{"title":"Local-MIP: Efficient local search for mixed integer programming","authors":"Peng Lin , Shaowei Cai , Mengchuan Zou , Jinkun Lin","doi":"10.1016/j.artint.2025.104405","DOIUrl":"10.1016/j.artint.2025.104405","url":null,"abstract":"<div><div>Mixed Integer Programming (MIP) is a fundamental model in operations research with broad industrial applications. Local search is a powerful methodology for solving complex optimization problems; however, the development of local search algorithms for MIP still needs exploration. In this work, we propose <em>Local-MIP</em>, an efficient local search algorithm tailored for MIP that integrates novel operators and employs a two-mode architecture to adaptively apply operators based on the current solution's feasibility. For the feasible mode, we propose the lift move operator and a corresponding lift process to improve the objective value while maintaining feasibility. For the infeasible mode, we propose the breakthrough move and mixed tight move operators to respectively optimize the objective function and satisfy constraints. To apply operators intelligently, we develop a dynamic weighting scheme that balances the priorities of the objective function and constraints. Furthermore, we propose a two-level scoring function structure that hierarchically selects operations, guiding the search toward high-quality feasible solutions. Experiments are conducted on public benchmarks to compare <em>Local-MIP</em> with state-of-the-art MIP solvers in finding high-quality solutions. The results show that <em>Local-MIP</em> significantly outperforms <em>CPLEX</em>, <em>HiGHS</em>, <em>SCIP</em>, and <em>Feasibility Jump</em> while remaining competitive with the commercial solver <em>Gurobi</em> on challenging problems within short time limits. Moreover, <em>Local-MIP</em> establishes 10 new records on MIPLIB open instances.</div></div>","PeriodicalId":8434,"journal":{"name":"Artificial Intelligence","volume":"348 ","pages":"Article 104405"},"PeriodicalIF":4.6,"publicationDate":"2025-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144922750","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}

引用次数: 0

Planning for temporally extended goals in pure-past linear temporal logic 在纯过去线性时间逻辑中规划时间扩展目标

IF 4.6 2区计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Artificial Intelligence

Pub Date : 2025-11-01 Epub Date: 2025-09-08 DOI: 10.1016/j.artint.2025.104409

Luigi Bonassi , Giuseppe De Giacomo , Marco Favorito , Francesco Fuggitti , Alfonso Emilio Gerevini , Enrico Scala

We study planning for temporally extended goals expressed in Pure-Past Linear Temporal Logic (ppltl) in the context of deterministic (i.e., classical) and fully observable nondeterministic (FOND) domains. ppltl is the variant of Linear-time Temporal Logic on finite traces (ltl_f) that refers to the past rather than the future. Although ppltl is as expressive as ltl_f, we show that it is computationally much more effective for planning. In particular, we show that checking the validity of a plan for a ppltl formula is Markovian. This is achieved by introducing a linear number of additional propositional variables that capture the validity of the entire formula in a modular fashion. The solution encoding introduces only a linear number of new fluents proportional to the size of the ppltl goal and does not require any additional spurious action. We implement our solution technique in a system called

Plan4Past

, which can be used alongside state-of-the-art classical and FOND planners. Our empirical analysis demonstrates the practical effectiveness of

Plan4Past

in both classical and FOND problems, showing that the resulting planner performs overall better than other planning approaches for ltl_f goals.

我们研究了在确定性（即经典）和完全可观察的非确定性（FOND）域的背景下，纯过去线性时间逻辑（ppltl）中表达的时间扩展目标的规划。ppltl是有限轨迹上的线性时间时间逻辑（ltlf）的变体，它指的是过去而不是未来。尽管ppltl与ltf一样具有表现力，但我们证明了它在规划方面的计算效率要高得多。特别地，我们证明了检验ppltl公式的计划有效性是马尔可夫的。这是通过引入线性数量的附加命题变量来实现的，这些变量以模块化的方式捕获整个公式的有效性。解决方案编码只引入与ppltl目标大小成比例的线性数量的新流，并且不需要任何额外的伪操作。我们在一个名为Plan4Past的系统中实现了我们的解决方案技术，该系统可以与最先进的经典规划和FOND规划一起使用。我们的实证分析证明了Plan4Past在经典问题和FOND问题中的实际有效性，表明所得到的规划器在实现终身目标方面的总体表现优于其他规划方法。

{"title":"Planning for temporally extended goals in pure-past linear temporal logic","authors":"Luigi Bonassi , Giuseppe De Giacomo , Marco Favorito , Francesco Fuggitti , Alfonso Emilio Gerevini , Enrico Scala","doi":"10.1016/j.artint.2025.104409","DOIUrl":"10.1016/j.artint.2025.104409","url":null,"abstract":"<div><div>We study planning for temporally extended goals expressed in Pure-Past Linear Temporal Logic (<span>ppltl</span>) in the context of deterministic (i.e., classical) and fully observable nondeterministic (FOND) domains. <span>ppltl</span> is the variant of Linear-time Temporal Logic on finite traces (<span>ltl</span><sub><em>f</em></sub>) that refers to the past rather than the future. Although <span>ppltl</span> is as expressive as <span>ltl</span><sub><em>f</em></sub>, we show that it is computationally much more effective for planning. In particular, we show that checking the validity of a plan for a <span>ppltl</span> formula is Markovian. This is achieved by introducing a linear number of additional propositional variables that capture the validity of the entire formula in a modular fashion. The solution encoding introduces only a linear number of new fluents proportional to the size of the <span>ppltl</span> goal and does not require any additional spurious action. We implement our solution technique in a system called <span><math><mi>Plan4Past</mi></math></span>, which can be used alongside state-of-the-art classical and FOND planners. Our empirical analysis demonstrates the practical effectiveness of <span><math><mi>Plan4Past</mi></math></span> in both classical and FOND problems, showing that the resulting planner performs overall better than other planning approaches for <span>ltl</span><sub><em>f</em></sub> goals.</div></div>","PeriodicalId":8434,"journal":{"name":"Artificial Intelligence","volume":"348 ","pages":"Article 104409"},"PeriodicalIF":4.6,"publicationDate":"2025-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145044398","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}

引用次数: 0

Social behavior as a key to learning-based multi-agent pathfinding dilemmas 社会行为是基于学习的多智能体寻径困境的关键

IF 4.6 2区计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Artificial Intelligence

Pub Date : 2025-11-01 Epub Date: 2025-07-30 DOI: 10.1016/j.artint.2025.104397

Chengyang He, Tanishq Duhan, Parth Tulsyan, Patrick Kim, Guillaume Sartoretti

The Multi-agent Path Finding (MAPF) problem involves finding collision-free paths for a team of agents in a known, static environment, with important applications in warehouse automation, logistics, or last-mile delivery. To meet the needs of these large-scale applications, current learning-based methods often deploy the same fully trained, decentralized network to all agents to improve scalability. However, such parameter sharing typically results in homogeneous behaviors among agents, which may prevent agents from breaking ties around symmetric conflict (e.g., bottlenecks) and might lead to live-/deadlocks. In this paper, we propose SYLPH, a novel learning-based MAPF framework aimed to mitigate the adverse effects of homogeneity by allowing agents to learn and dynamically select different social behaviors (akin to individual, dynamic roles), without affecting the scalability offered by parameter sharing. Specifically, SYLPH offers a novel hierarchical mechanism by introducing Social Value Orientation (SVO) as a temporally extended latent variable that plays a central role in both policy generation and reward assignment. To support this hierarchical decision-making process, we introduce Social-aware Multi-Policy PPO (SMP3O), a reinforcement learning method that ensures stable and effective training through a mechanism for the cross-utilization of advantages. Moreover, we design an SVO-based learning tie-breaking algorithm, allowing agents to proactively avoid collisions, rather than relying solely on post-processing techniques. As a result of this hierarchical decision-making and exchange of social preferences, SYLPH endows agents with the ability to reason about the MAPF task through more latent spaces and nuanced contexts, leading to varied responses that can help break ties around symmetric conflicts. Our comparative experiments show that SYLPH achieves state-of-the-art performance, surpassing other learning-based MAPF planners in random, room-like, and maze-like maps, while our ablation studies demonstrate the advantages of each component in SYLPH. We finally experimentally validate our trained policies on hardware in three types of maps, showing how SYLPH allows agents to find high-quality paths under real-life conditions. Our code and videos are available at: marmotlab.github.io/mapf_sylph.

多代理寻路（Multi-agent Path Finding， MAPF）问题涉及在已知的静态环境中为一组代理寻找无冲突的路径，在仓库自动化、物流或最后一英里交付中具有重要应用。为了满足这些大规模应用程序的需求，当前基于学习的方法通常为所有代理部署相同的经过充分训练的分散网络，以提高可扩展性。然而，这种参数共享通常会导致代理之间的同质行为，这可能会阻止代理打破围绕对称冲突（例如，瓶颈）的联系，并可能导致活锁/死锁。在本文中，我们提出了SYLPH，这是一种新的基于学习的MAPF框架，旨在通过允许智能体学习和动态选择不同的社会行为（类似于个体的动态角色），而不影响参数共享提供的可扩展性，从而减轻同质性的不利影响。具体而言，SYLPH通过引入社会价值取向（SVO）作为一个在政策制定和奖励分配中发挥核心作用的时间扩展潜在变量，提供了一种新的分层机制。为了支持这种分层决策过程，我们引入了社会感知多策略PPO (smp30)，这是一种强化学习方法，通过交叉利用优势的机制确保稳定有效的训练。此外，我们设计了一种基于svo的学习断绳算法，允许智能体主动避免碰撞，而不是仅仅依赖后处理技术。由于这种分层决策和社会偏好的交换，SYLPH赋予智能体通过更多潜在空间和微妙背景来推理MAPF任务的能力，从而导致不同的反应，有助于打破对称冲突周围的联系。我们的对比实验表明，SYLPH达到了最先进的性能，在随机、房间和迷宫地图中超越了其他基于学习的MAPF规划器，而我们的消融研究表明了SYLPH中每个组件的优势。最后，我们在三种类型的地图上通过实验验证了我们在硬件上训练好的策略，展示了SYLPH如何允许智能体在现实条件下找到高质量的路径。我们的代码和视频可在：marmotlab.github.io/mapf_sylph。

{"title":"Social behavior as a key to learning-based multi-agent pathfinding dilemmas","authors":"Chengyang He, Tanishq Duhan, Parth Tulsyan, Patrick Kim, Guillaume Sartoretti","doi":"10.1016/j.artint.2025.104397","DOIUrl":"10.1016/j.artint.2025.104397","url":null,"abstract":"<div><div>The Multi-agent Path Finding (MAPF) problem involves finding collision-free paths for a team of agents in a known, static environment, with important applications in warehouse automation, logistics, or last-mile delivery. To meet the needs of these large-scale applications, current learning-based methods often deploy the same fully trained, decentralized network to all agents to improve scalability. However, such parameter sharing typically results in homogeneous behaviors among agents, which may prevent agents from breaking ties around symmetric conflict (e.g., bottlenecks) and might lead to live-/deadlocks. In this paper, we propose SYLPH, a novel learning-based MAPF framework aimed to mitigate the adverse effects of homogeneity by allowing agents to learn and dynamically select different social behaviors (akin to individual, dynamic roles), without affecting the scalability offered by parameter sharing. Specifically, SYLPH offers a novel hierarchical mechanism by introducing Social Value Orientation (SVO) as a temporally extended latent variable that plays a central role in both policy generation and reward assignment. To support this hierarchical decision-making process, we introduce Social-aware Multi-Policy PPO (SMP3O), a reinforcement learning method that ensures stable and effective training through a mechanism for the cross-utilization of advantages. Moreover, we design an SVO-based learning tie-breaking algorithm, allowing agents to proactively avoid collisions, rather than relying solely on post-processing techniques. As a result of this hierarchical decision-making and exchange of social preferences, SYLPH endows agents with the ability to reason about the MAPF task through more latent spaces and nuanced contexts, leading to varied responses that can help break ties around symmetric conflicts. Our comparative experiments show that SYLPH achieves state-of-the-art performance, surpassing other learning-based MAPF planners in random, room-like, and maze-like maps, while our ablation studies demonstrate the advantages of each component in SYLPH. We finally experimentally validate our trained policies on hardware in three types of maps, showing how SYLPH allows agents to find high-quality paths under real-life conditions. Our code and videos are available at: <span><span>marmotlab.github.io/mapf_sylph</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":8434,"journal":{"name":"Artificial Intelligence","volume":"348 ","pages":"Article 104397"},"PeriodicalIF":4.6,"publicationDate":"2025-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144739690","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}

引用次数: 0

On preference learning based on sequential Bayesian optimization with pairwise comparison 基于两两比较序列贝叶斯优化的偏好学习

IF 4.6 2区计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Artificial Intelligence

Pub Date : 2025-11-01 Epub Date: 2025-08-28 DOI: 10.1016/j.artint.2025.104400

Tanya Ignatenko , Kirill Kondrashov , Marco Cox , Bert de Vries

User preference learning is generally a hard problem. Individual preferences are typically unknown even to users themselves, while the space of choices is infinite. Here we study user preference learning from information-theoretic perspective. We model preference learning as a system with two interacting sub-systems, one representing a user with his/her preferences and another one representing an agent that has to learn these preferences. The user with his/her behavior is modeled by a parametric preference function. To efficiently learn the preferences and reduce search space quickly, we propose the agent that interacts with the user to collect the most informative data for learning. The agent presents two proposals to the user for evaluation, and the user rates them based on his/her preference function. We show that the optimum agent strategy for data collection and preference learning is a result of maximin optimization of the normalized weighted Kullback-Leibler (KL) divergence between true and agent-assigned predictive user response distributions. The resulting value of the KL-divergence, which we also call of a remaining system uncertainty (RSU), provides an efficient performance metric in the absence of the ground truth. This metric characterizes how well the agent can predict user and, thus, the quality of the underlying learned user (preference) model. Our proposed agent comprises sequential mechanisms for user model inference and proposal generation. To infer the user model (preference function), Bayesian approximate inference is used in the agent. The data collection strategy is to generate proposals, responses to which help resolving uncertainty associated with prediction of the user responses the most. The efficiency of our approach is validated by numerical simulations. Also a real-life example of preference learning application is provided.

用户偏好学习通常是一个难题。个人偏好通常连用户自己都不知道，而选择的空间是无限的。本文从信息论的角度研究用户偏好学习。我们将偏好学习建模为具有两个交互子系统的系统，一个代表具有其偏好的用户，另一个代表必须学习这些偏好的代理。用户和他/她的行为通过参数偏好函数建模。为了有效地学习用户偏好并快速减少搜索空间，我们提出了与用户交互的智能体来收集最具信息量的数据进行学习。智能体向用户提出两个建议供用户评价，用户根据自己的偏好函数对其进行评分。我们表明，用于数据收集和偏好学习的最优代理策略是真实和代理分配的预测用户响应分布之间的标准化加权Kullback-Leibler （KL）散度的最大优化结果。kl -散度的结果值，我们也称之为剩余系统不确定性（RSU），在没有基础真值的情况下提供了一个有效的性能度量。这个指标描述了代理预测用户的能力，从而描述了底层学习到的用户（偏好）模型的质量。我们提出的智能体包括用户模型推理和建议生成的顺序机制。为了推断用户模型（偏好函数），在代理中使用贝叶斯近似推理。数据收集策略是生成建议和响应，这些建议和响应最有助于解决与预测用户响应相关的不确定性。数值仿真验证了该方法的有效性。此外，还提供了一个实际应用的偏好学习实例。

{"title":"On preference learning based on sequential Bayesian optimization with pairwise comparison","authors":"Tanya Ignatenko , Kirill Kondrashov , Marco Cox , Bert de Vries","doi":"10.1016/j.artint.2025.104400","DOIUrl":"10.1016/j.artint.2025.104400","url":null,"abstract":"<div><div>User preference learning is generally a hard problem. Individual preferences are typically unknown even to users themselves, while the space of choices is infinite. Here we study user preference learning from information-theoretic perspective. We model preference learning as a system with two interacting sub-systems, one representing a user with his/her preferences and another one representing an agent that has to learn these preferences. The user with his/her behavior is modeled by a parametric preference function. To efficiently learn the preferences and reduce search space quickly, we propose the agent that interacts with the user to collect the most informative data for learning. The agent presents two proposals to the user for evaluation, and the user rates them based on his/her preference function. We show that the optimum agent strategy for data collection and preference learning is a result of maximin optimization of the normalized weighted Kullback-Leibler (KL) divergence between true and agent-assigned predictive user response distributions. The resulting value of the KL-divergence, which we also call of a remaining system uncertainty (RSU), provides an efficient performance metric in the absence of the ground truth. This metric characterizes how well the agent can predict user and, thus, the quality of the underlying learned user (preference) model. Our proposed agent comprises sequential mechanisms for user model inference and proposal generation. To infer the user model (preference function), Bayesian approximate inference is used in the agent. The data collection strategy is to generate proposals, responses to which help resolving uncertainty associated with prediction of the user responses the most. The efficiency of our approach is validated by numerical simulations. Also a real-life example of preference learning application is provided.</div></div>","PeriodicalId":8434,"journal":{"name":"Artificial Intelligence","volume":"348 ","pages":"Article 104400"},"PeriodicalIF":4.6,"publicationDate":"2025-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145018407","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}

引用次数: 0

Choosing abstraction levels for model-based software debugging: A theoretical and empirical analysis for spreadsheet programs 为基于模型的软件调试选择抽象层次：对电子表格程序的理论和实证分析

IF 4.6 2区计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Artificial Intelligence

Pub Date : 2025-11-01 Epub Date: 2025-08-20 DOI: 10.1016/j.artint.2025.104399

Patrick Rodler , Birgit Hofer , Dietmar Jannach , Iulia Nica , Franz Wotawa

Model-based diagnosis is a generally applicable, principled approach to the systematic debugging of a wide range of system types such as circuits, knowledge bases, physical devices, or software. Based on a formal description of the system, it enables precise and deterministic reasoning about potential faults responsible for observed misbehavior. In software, such a formal system description can often even be extracted from the buggy program fully automatically. As logical reasoning is central to diagnosis, the performance of model-based debuggers is largely influenced by reasoning efficiency, which in turn depends on the complexity and expressivity of the system description. Since highly detailed models capturing exact semantics often exceed the capabilities of current reasoning tools, researchers have proposed more abstract representations.

In this work, we thoroughly analyze system modeling techniques with a focus on fault localization in spreadsheets—one of the most widely used end-user programming paradigms. Specifically, we present three constraint model types characterizing spreadsheets at different abstraction levels, show how to extract them automatically from faulty spreadsheets, and provide theoretical and empirical investigations of the impact of abstraction on both diagnostic output and computational performance. Our main conclusions are that (i) for the model types, there is a trade-off between the conciseness of generated fault candidates and computation time, (ii) the exact model is often impractical, and (iii) a new model based on qualitative reasoning yields the same solutions as the exact one in up to more than half the cases while being orders of magnitude faster.

Due to their ability to restrict the solution space in a sound way, the explored model-based techniques, rather than being used as standalone approaches, are expected to realize their full potential in combination with iterative sequential diagnosis or indeterministic but more performant statistical debugging methods.

基于模型的诊断是一种普遍适用的、有原则的方法，可以对各种系统类型（如电路、知识库、物理设备或软件）进行系统调试。基于系统的形式化描述，它能够对导致观察到的不当行为的潜在故障进行精确和确定的推理。在软件中，这种正式的系统描述通常甚至可以完全自动地从有缺陷的程序中提取出来。由于逻辑推理是诊断的核心，基于模型的调试器的性能在很大程度上受到推理效率的影响，而推理效率又取决于系统描述的复杂性和表达性。由于捕获精确语义的高度详细的模型通常超过当前推理工具的能力，研究人员提出了更抽象的表示。

{"title":"Choosing abstraction levels for model-based software debugging: A theoretical and empirical analysis for spreadsheet programs","authors":"Patrick Rodler , Birgit Hofer , Dietmar Jannach , Iulia Nica , Franz Wotawa","doi":"10.1016/j.artint.2025.104399","DOIUrl":"10.1016/j.artint.2025.104399","url":null,"abstract":"<div><div>Model-based diagnosis is a generally applicable, principled approach to the systematic debugging of a wide range of system types such as circuits, knowledge bases, physical devices, or software. Based on a formal description of the system, it enables precise and deterministic reasoning about potential faults responsible for observed misbehavior. In software, such a formal system description can often even be extracted from the buggy program fully automatically. As logical reasoning is central to diagnosis, the performance of model-based debuggers is largely influenced by reasoning efficiency, which in turn depends on the complexity and expressivity of the system description. Since highly detailed models capturing exact semantics often exceed the capabilities of current reasoning tools, researchers have proposed more abstract representations.</div><div>In this work, we thoroughly analyze system modeling techniques with a focus on fault localization in spreadsheets—one of the most widely used end-user programming paradigms. Specifically, we present three constraint model types characterizing spreadsheets at different abstraction levels, show how to extract them automatically from faulty spreadsheets, and provide theoretical and empirical investigations of the impact of abstraction on both diagnostic output and computational performance. Our main conclusions are that <em>(i)</em> for the model types, there is a trade-off between the conciseness of generated fault candidates and computation time, <em>(ii)</em> the exact model is often impractical, and <em>(iii)</em> a new model based on qualitative reasoning yields the same solutions as the exact one in up to more than half the cases while being orders of magnitude faster.</div><div>Due to their ability to restrict the solution space in a sound way, the explored model-based techniques, rather than being used as standalone approaches, are expected to realize their full potential in combination with iterative sequential diagnosis or indeterministic but more performant statistical debugging methods.</div></div>","PeriodicalId":8434,"journal":{"name":"Artificial Intelligence","volume":"348 ","pages":"Article 104399"},"PeriodicalIF":4.6,"publicationDate":"2025-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144898569","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}

引用次数: 0