Modeling visual problem solving as analogical reasoning.
The DOI matches its Crossref record; 96 of the 96 references it cites were found in a registry or an index.
Abstract
We present a computational model of visual problem solving, designed to solve problems from the Raven's Progressive Matrices intelligence test. The model builds on the claim that analogical reasoning lies at the heart of visual problem solving, and intelligence more broadly. Images are compared via structure mapping, aligning the common relational structure in 2 images to identify commonalities and differences. These commonalities or differences can themselves be reified and used as the input for future comparisons. When images fail to align, the model dynamically rerepresents them to facilitate the comparison. In our analysis, we find that the model matches adult human performance on the Standard Progressive Matrices test, and that problems which are difficult for the model are also difficult for people. Furthermore, we show that model operations involving abstraction and rerepresentation are particularly difficult for people, suggesting that these operations may be critical for performing visual problem solving, and reasoning more generally, at the highest level. (PsycINFO Database Record
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Often this involves a process of re-representation , in which an initial problem representation is revised so as to facilitate the discovery of an analogy. 36-38”
From Emergent analogical reasoning in large language models (2023) · cites this paper as [38]
In the citing paper
“Human reasoners are capable of identifying abstract similarities between situations even when these situations are superficially quite different.”
From Emergent analogical reasoning in large language models (2023) · cites this paper as [38]
Citations
Cites
Discrete-Time Signal Processing
Oppenheim, A. V., & Schafer, R. W. (1989) · Cited by 12,571
Mental Rotation of Three-Dimensional Objects
Shepard, R. N., & Metzler, J. (1971) · Science · doi:10.1126/science.171.3972.701 · Cited by 6,246
Recognition-by-components: A theory of human image understanding.
Biederman, I. (1987) · Psychological Review · doi:10.1037/0033-295x.94.2.115 · Cited by 5,621
(1998) · Cited by 4,172
Forest before trees: The precedence of global features in visual perception
Navon, D. (1977) · Cognitive Psychology · doi:10.1016/0010-0285(77)90012-3 · Cited by 4,005
Ericsson, K. A., & Kintsch, W. (1995) · Psychological Review · doi:10.1037/0033-295x.102.2.211 · Cited by 3,498
Schema induction and analogical transfer
Gick, M. L., & Holyoak, K. J. (1983) · Cognitive Psychology · doi:10.1016/0010-0285(83)90002-6 · Cited by 3,010
Theory of fluid and crystallized intelligence: A critical experiment.
Cattell, R. B. (1963) · Journal of Educational Psychology · doi:10.1037/h0046743 · Cited by 2,536
Representation and recognition of the spatial organization of three-dimensional shapes
Marr, D., & Nishihara, H. K. (1978) · Proceedings of the Royal Society of London. Series B. Biological Sciences · doi:10.1098/rspb.1978.0020 · Cited by 2,158
Image And Brain: The Resolution of the Imagery Debate
Kosslyn, S. M. (1994) · doi:10.7551/mitpress/3653.001.0001 · Cited by 1,977
Cited by
Emergent analogical reasoning in large language models
Webb, T., Holyoak, K. J., & Lu, H. (2023) · Nature Human Behaviour · doi:10.1038/s41562-023-01659-w · Cited by 404
RAVEN: A Dataset for Relational and Analogical Visual REasoNing
Zhang, C., Gao, F., Jia, B., Zhu, Y., & Zhu, S.-C. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00546 · Cited by 175
“However, an oversimplified assumption was usually made in the experiments that the computer programs had access to a symbolic representation of the image and the operations of rules [7, 32, 33, 34].”
BackgroundMethodResultInfluentialAbstraction and analogy‐making in artificial intelligence
Mitchell, M. (2021) · Annals of the New York Academy of Sciences · doi:10.1111/nyas.14619 · Cited by 125
“This example is one of the easier RPM problems; often they involve more than two shapes per square and changes in multiple attributes (shape, color, position, number, etc.) Lovett et al. 72 used SME as one component of a system to solve RPM problems.”
MethodInfluentialStratified Rule-Aware Network for Abstract Visual Reasoning
Hu, S., Ma, Y., Liu, X., Wei, Y., & Bai, S. (2021) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v35i2.16248 · Cited by 147
“Computational models for RPM in the cognitive science community access symbolic representations of the images (Carpenter, Just, and Shell 1990; Lovett and Forbus 2017; Lovett, Forbus, and Usher 2010; Lovett et al. 2010).”
Representation and Computation in Cognitive Models
Forbus, K. D., Liang, C., & Rabkina, I. (2017) · Topics in Cognitive Science · doi:10.1111/tops.12277 · Cited by 69
Self-citationZwart, D. P., Noroozi, O., Luit, J. E. H. V., Goei, S. L., & Nieuwenhuis, A. F. M. (2020) · Nurse Education in Practice · doi:10.1016/j.nepr.2020.102755 · Cited by 86
Abstract Spatial-Temporal Reasoning via Probabilistic Abduction and Execution
Zhang, C., Jia, B., Zhu, S. C., & Zhu, Y. (2021) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr46437.2021.00961 · Cited by 79
“Psychologists have proposed reasoning systems based on symbolic representations and discrete logics [3, 37, 38, 39].”
BackgroundMulti-Label Contrastive Learning for Abstract Visual Reasoning
Małkiński, M., & Mańdziuk, J. (2022) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2022.3185949 · Cited by 57
“Previous studies have shown that the ability to make analogies and contrasting experiences is a key ingredient of human intelligence [10], [11], [20], [21].”
BackgroundThe Raven’s Coloured Progressive Matrices in Healthy Children: A Qualitative Approach
Smirni, D. (2020) · Brain Sciences · doi:10.3390/brainsci10110877 · Cited by 48
“Similarly, Lovett and Forbuss [52], claiming that analogical reasoning is crucial in the visual problem solving, devised a computational model to solve visual problems from the Raven’s Progressive Matrices.”
BackgroundModeling visuospatial reasoning
Reed, S. K. (2018) · Spatial Cognition and Computation · doi:10.1080/13875868.2018.1460751 · Cited by 33
“The Lovett and Forbus (2017) model therefore uses both qualitative representations for comparison and reasoning and quantitative information for computing shape transformations.”
BackgroundMethodA Closer Look at Generalisation in RAVEN
Spratley, S., Ehinger, K. A., & Miller, T. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-58583-9_36 · Cited by 45
Spatial alignment facilitates visual comparison.
Matlen, B. J., Dedre Gentner, C., & Franconeri, S. (2020) · Journal of Experimental Psychology Human Perception & Performance · doi:10.1037/xhp0000726 · Cited by 29
“Many researchers have proposed that analogical comparison processes are used to process visual comparisons for visuals that, like the ones used here, contain elements in spatial configurations (Doumas et al., 2008; Gattis, 2002; Kotovsky & Gentner, 1996; Lovett & Forbus, 2017; Sagi et al., 2012).”
BackgroundRAVEN: A Dataset for Relational and Analogical Visual rEasoNingPreprint
Zhang, C., Gao, F., Jia, B., Zhu, Y., & Zhu, S. C. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1903.02741 · Cited by 28
“However, an oversimplified assumption was usually made in the experiments that the computer programs had access to a symbolic representation of the image and the operations of rules [7, 32, 33, 34].”
BackgroundMethodResultInfluentialShea, N. J. (2024) · doi:10.1093/9780191997167.001.0001 · Cited by 36
Analogy and Qualitative Representations in the Companion Cognitive Architecture
Forbus, K. D., & Hinrichs, T. R. (2017) · AI Magazine · doi:10.1609/aimag.v38i4.2743 · Cited by 44
Self-citationQualitative Representations: How People Reason and Learn about the Continuous World
Forbus, K. D. (2019) · The MIT Press eBooks · doi:10.7551/mitpress/11578.001.0001 · Cited by 71
Self-citationProcess-oriented intelligence research: A review from the cognitive perspective
Frischkorn, G. T., Wilhelm, O., & Oberauer, K. (2022) · Intelligence · doi:10.1016/j.intell.2022.101681 · Cited by 32
Topological Relations Between Objects Are Categorically Coded
Lovett, A., & Franconeri, S. (2017) · Psychological Science · doi:10.1177/0956797617709814 · Cited by 27
“…it possible to isolate whether the set of categorical relations we tested brings the strongest benefit at the encoding, retrieval, or comparison stages of processing, although the computational models (Lovett & Forbus, 2011a, 2017; Lovett et al., 2009) posit the strongest role during comparison.”
BackgroundSelf-citationMachine Number Sense: A Dataset of Visual Arithmetic Problems for Abstract and Relational Reasoning
Zhang, W.-H., Zhang, C., Zhu, Y., & Zhu, S.-C. (2020) · AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v34i02.5489 · Cited by 34
“visual objects as a set of abstract concepts and variation rules (Lovett et al. 2010; Lovett, Forbus, and Usher 2010; Lovett and Forbus 2017).”
BackgroundWhat Does the Chart Say? Grouping Cues Guide Viewer Comparisons and Conclusions in Bar Charts
Xiong, C., Stokes, C., Lovett, A., & Franconeri, S. (2023) · IEEE Transactions on Visualization and Computer Graphics · doi:10.1109/tvcg.2023.3289292 · Cited by 22
“An analysis of a popular visual intelligence test indicated that this process, known as perceptual reorganization , is required by some of the most difficult problems on the test [46], suggesting that individuals would rarely perform such a process while viewing a chart.”
BackgroundSelf-citationZero-shot visual reasoning through probabilistic analogical mapping
Webb, T. W., Fu, S., Bihl, T., Holyoak, K. J., & Lu, H. (2023) · Nature Communications · doi:10.1038/s41467-023-40804-x · Cited by 28
“A few recent studies have applied a more traditional cognitive model of analogical mapping, the Structure-Mapping Engine (SME), to visual analogy problems involving simple geometric forms 36,37 .”
Zero-shot visual reasoning through probabilistic analogical mapping
Webb, T. W., Fu, S., Bihl, T., Holyoak, K. J., & Lu, H. (2022) · arXiv · doi:10.48550/arxiv.2209.15087 · Cited by 18
“A few recent studies have applied a more traditional cognitive model of analogical mapping, the Structure-Mapping Engine (SME), to visual analogy problems involving simple geometric forms 36,37 .”
Combs, K., Lu, H., & Bihl, T. (2023) · Algorithms · doi:10.3390/a16030146 · Cited by 24
“was re-utilized for visual problems [85,86].”
The Cognitive Science of Sketch Worksheets
Forbus, K. D., Chang, M., McLure, M. D., & Usher, M. (2017) · Topics in Cognitive Science · doi:10.1111/tops.12262 · Cited by 17
Self-citationSelective Replay Enhances Learning in Online Continual Analogical Reasoning
Hayes, T. L., & Kanan, C. (2021) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw53098.2021.00389 · Cited by 28
“One of the characteristics of human intelligence that distinguishes us over other animals is our ability to perform analogical reasoning [27, 30, 55].”
BackgroundHélie, S., & Pizlo, Z. (2021) · Topics in Cognitive Science · doi:10.1111/tops.12572 · Cited by 18
Falomir, Z., & Plaza, E. (2019) · Annals of Mathematics and Artificial Intelligence · doi:10.1007/s10472-019-09619-9 · Cited by 16
“As qualitative descriptors are suitable for modelling human spatial reasoning [13, 18, 35], a relation can be established between image schemas and qualitative descriptors, as some examples shown in Table 1.”
MethodHuman-Like Sketch Object Recognition via Analogical Learning
Chen, K., Rabkina, I., McLure, M. D., & Forbus, K. D. (2019) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v33i01.33011336 · Cited by 17
Self-citationHierarchical Rule Induction Network for Abstract Visual Reasoning.Preprint
Hu, S., Ma, Y., Liu, X., Wei, Y., & Bai, S. (2020) · arXiv (Cornell University) · Cited by 15
Learning Algebraic Representation for Systematic Generalization in Abstract Reasoning
Zhang, C., Xie, S., Jia, B., Wu, Y. N., Zhu, S. C., & Zhu, Y. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-19842-7_40 · Cited by 31
Action Recognition From Skeleton Data via Analogical Generalization Over Qualitative Representations
Chen, K., & Forbus, K. D. (2018) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v32i1.11328 · Cited by 14
Self-citationShipley, T. F., & Tikoff, B. (2018) · Journal of Structural Geology · doi:10.1016/j.jsg.2018.05.007 · Cited by 12
“…spatial reasoning in Arti fi cial Intelligence (AI) has led to impressive accomplishments in analogical reasoning, such as recognizing pattern progressions in Ravens progressive matrices (Lovett and Forbus, 2017), the application to general reasoning and novel problems is still in the future.”
BackgroundPolitical Machines: Ethical Governance in the Age of AI
McEvoy, F. J. (2019) · Moral Philosophy and Politics · doi:10.1515/mopp-2019-0004 · Cited by 15
AI, visual imagery, and a case study on the challenges posed by human intelligence tests
Kunda, M. (2020) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.1912335117 · Cited by 13
“Many artificial agents reason about visuospatial information using nonimagery-based representations (33); for example, visuospatial domain knowledge can be encoded propositionally, such as the rule left-of (x,y) =⇒ right-of (y,x).”
BackgroundA Neuro-Symbolic Reasoning Model on Raven's Progressive Matrices
Zhao, S., You, H., Zhang, R., Si, B., Zhen, Z., Wan, X., & Wang, D.-H. (2022) · Cognitive Computation · doi:10.1007/s12559-023-10154-3 · Cited by 12
“This process mimicked the hierarchical processing of humans, who perceive at different levels and compare at different scales [11].”
BackgroundMethodInfluentialLogical composition of qualitative shapes applied to solve spatial reasoning tests
Pich, A., & Falomir, Z. (2018) · Cognitive Systems Research · doi:10.1016/j.cogsys.2018.06.002 · Cited by 10
VASR: Visual Analogies of Situation Recognition
Bitton, Y., Yosef, R., Strugo, E., Shahaf, D., Schwartz, R., & Stanovsky, G. (2023) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v37i1.25096 · Cited by 33
Seeing the Meaning: Vision Meets Semantics in Solving Pictorial Analogy Problems.
Lu, H., Liu, Q., Ichien, N., Yuille, A., & Holyoak, K. J. (2019) · Cognitive Science · Cited by 17
Pluck, G. C. (2018) · Psychological Reports · doi:10.1177/0033294118762589 · Cited by 14
“Artificial intelligence, also a rapidly progressing science, is benefiting from understanding human intelligence (Lovett & Forbus, 2017).”
BackgroundIndividual Differences in Reward‐Based Learning Predict Fluid Reasoning Abilities
Stocco, A., Prat, C. S., & Graham, L. K. (2021) · Cognitive Science · doi:10.1111/cogs.12941 · Cited by 16
Experts Collaboration Learning for Continual Multi-Modal Reasoning
Xu, L. H., & Liu, J. (2023) · IEEE Transactions on Image Processing · doi:10.1109/tip.2023.3310336 · Cited by 9
“g, analogical reasoning [3], [4]) lies at the core of the high-level”
BackgroundTHINKING-LOOP: The Semantic Vector Driven Closed-Loop Model for Brain Computing
Kuai, H., Zhang, X., Yang, Y., Chen, J., Shi, B., & Zhong, N. (2020) · IEEE Access · doi:10.1109/access.2019.2963070 · Cited by 9
“These results are consistent with current cognitive theory and previous fMRI studies, on the one hand, which emphasizes the correlation between reasoning and problem solving [43].”
ResultSame/different in visual reasoning
Forbus, K. D., & Lovett, A. (2020) · Current Opinion in Behavioral Sciences · doi:10.1016/j.cobeha.2020.09.008 · Cited by 14
Self-citationTowards Fluid Machine Intelligence: Can We Make a Gifted AI?
Davidson, I. A. K., & Walker, P. B. (2019) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v33i01.33019760 · Cited by 11
“Work that directly takes the images and requires minimal human involvement has only recently been explored (Lovett and Forbus 2017).”
BackgroundA model of symbolic processing in Raven’s progressive matrices
Raudies, F., & Hasselmo, M. E. (2017) · Biologically Inspired Cognitive Architectures · doi:10.1016/j.bica.2017.07.003 · Cited by 9
Special issue on problem-solving, creativity and spatial reasoning
Falomir, Z., & Oltețeanu, A. (2019) · Cognitive Systems Research · doi:10.1016/j.cogsys.2019.05.001 · Cited by 9
LLMs as models for analogical reasoning
Musker, S., Duchnowski, A., Millière, R., & Pavlick, E. (2025) · Journal of Memory and Language · doi:10.1016/j.jml.2025.104676 · Cited by 46
“For example, Mitchell and Hofstadter’s Copycat models (Hofstadter & Mitchell, 1995) addressed re-representation but in the domain of letter string analogies, while subsequent work addressed re-representation in a synthetic Raven’s matrices domain (Lovett & Forbus, 2017).”
Spatial Alignment Facilitates Visual Comparison in Children
Zheng, Y. S., Matlen, B. J., & Gentner, D. (2022) · Cognitive Science · doi:10.1111/cogs.13182 · Cited by 16
“Visual comparison has been analyzed using the structure-mapping framework (Gattis, 2002; Lovett & Forbus, 2017; Markman & Gentner, 1993a; Sagi, Gentner, & Lovett, 2012; Yuan et al., 2017).”
BackgroundMethodFluid Intelligence Emerges from Representing Relations
Chuderski, A. (2022) · Journal of Intelligence · doi:10.3390/jintelligence10030051 · Cited by 11
“…tasks most strongly involving fluid reasoning (explicitly called relational reasoning; Holyoak 2012): analogical reasoning (Forbus et al. 1994; Halford et al. 2010; Keane et al. 1994) and inductive reasoning in matrix problems (e.g., the RAPM test; Carpenter et al. 1990; Lovett and Forbus 2017).”
BackgroundEvidence from machines that learn and think like people
Forbus, K. D., & Gentner, D. (2017) · Behavioral and Brain Sciences · doi:10.1017/s0140525x17000139 · Cited by 8
Self-citationAnalisis Kemampuan Penalaran Analogis Siswa SMP dalam Menyelesaikan Masalah Matematika
Ridho’i, M., Sulandra, I. M., Sukoryanto, S., & Nusantara, T. (2021) · Jurnal Pendidikan Matematika dan Sains · doi:10.21831/jpms.v8i1.19649 · Cited by 7
Wong, T. T., & Morsanyi, K. (2022) · Thinking & Reasoning · doi:10.1080/13546783.2022.2095031 · Cited by 7
Similarity-Based Reasoning, Raven's Matrices, and General Intelligence
Mekik, C. S., Sun, R., & Dai, D. Y. (2018) · International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2018/218 · Cited by 20
“This broad paradigm has encouraged work on analogical mechanisms for rule discovery [Lovett and Forbus, 2017; Rasmussen and Eliasmith, 2011], offering architectural insights for addressing the challenge of generality.”
BackgroundInfluentialCase-based prediction – A survey
Badra, F., & Lesot, M. (2023) · International Journal of Approximate Reasoning · doi:10.1016/j.ijar.2023.108920 · Cited by 11
Lailiyah, S., Kusaeri, K., Retnowati, E., & Erman, E. (2022) · JRAMathEdu (Journal of Research and Advances in Mathematics Education) · doi:10.23917/jramathedu.v7i3.17527 · Cited by 7
“It is a basic process in solving everyday problems (Ayal et al., 2016; Lovett & Forbus, 2017; Meheus, 2000; Supratman, 2019), making conclusions (Holyoak, 2012), and training high-order thinking (Richland & Begolli, 2016; Richland & Simms, 2015).”
BackgroundSketch Recognition via Part-based Hierarchical Analogical Learning
Chen, K., Forbus, K., Srinivasan, B. V., Chhaya, N., & Usher, M. (2023) · International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2023/331 · Cited by 5
“Analogical matching is handled by the Structure Mapping Engine (SME) [ Forbus et al. , 2017 ] , analogical retrieval by MAC/FAC [ Forbus et al. , 1995 ] , and analogical generalization is performed by the Sequential Analogical Generalization Engine (SAGE) [ McLure et al. , 2015b ] .”
MethodSelf-citationSystem analytics of data redundancy of corporate information systems using the theory of symmetry
Kopnova, O., Aitymova, A., & Abildinova, G. (2023) · Digital models and solutions · doi:10.29141/2949-477x-2023-2-3-4 · Cited by 5
Can LLMs Aid Analogical Reasoning for Strategic Decisions? A Comparative Study
Sen, P., Workiewicz, M., & Puranam, P. (2025) · Strategy Science · doi:10.1287/stsc.2025.0426 · Cited by 11
An interactive game for training reasoning about paper folding
Falomir, Z., Tarin, R., Puerta, A., & Garcia-Segarra, P. (2020) · Multimedia Tools and Applications · doi:10.1007/s11042-020-09830-5 · Cited by 7
Visual Relation Detection using Hybrid Analogical Learning
Chen, K., & Forbus, K. (2021) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v35i1.16162 · Cited by 5
“, 2011), a model of human visual perception that relies on analogical matching and relational structure, can solve mental rotation and paper folding tasks using SME, and performs better than most adult Americans on Raven’s Progressive Matrices (Lovett and Forbus, 2017).”
InfluentialSelf-citationGiancola, M., Pino, M. C., Riccio, V., Piccardi, L., & D’Amico, S. (2023) · Children · doi:10.3390/children10040630 · Cited by 4
“This aligns with previous research suggesting that analogical reasoning lies at the heart of visual problem solving and intelligence more broadly [48].”
ResultEntrepreneurial Food Ecosystem: Strategic Driver to Boost Resilience and Sustainability
Bernardi, P. D., & Azucar, D. (2019) · Contributions to management science · doi:10.1007/978-3-030-33502-1_5 · Cited by 4
Hua, T., & Kunda, M. (2020) · eScholarship (California Digital Library) · Cited by 4
Graph Mapping: A novel and simple test to validly assess fluid reasoning
Jastrzębski, J., Ociepka, M., & Chuderski, A. (2022) · Behavior Research Methods · doi:10.3758/s13428-022-01846-z · Cited by 6
“More recently, structure mapping was considered the key mechanism for a range of reasoning processes beyond analogy (Holyoak, 2012), including fluid reasoning (Lovett & Forbus, 2017).”
BackgroundA Memory-Augmented Neural Network Model of Abstract Rule LearningPreprint
Sinha, I., Webb, T. W., & Cohen, J. D. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2012.07172 · Cited by 7
“[6] and a recent extension of the Structure Mapping Engine [9, 28].”
BackgroundSketch Worksheets in Science, Technology, Engineering, and Mathematics Classrooms: Two Deployments
Forbus, K. D., Garnier, B. C., Tikoff, B., Marko, W. T., Usher, M., & McLure, M. D. (2020) · AI Magazine · doi:10.1609/aimag.v41i1.5189 · Cited by 3
Self-citationCan we automate diagrammatic reasoning?
Sekh, A. A., Dogra, D. P., Kar, S., Roy, P. P., & Prasad, D. K. (2020) · Pattern Recognition · doi:10.1016/j.patcog.2020.107412 · Cited by 3
Raven's Progressive Matrices Completion with Latent Gaussian Process Priors
Shi, F., Li, B., & Xue, X. (2021) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v35i11.17157 · Cited by 4
Nath, C. D., & Hazarika, S. M. (2021) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2021.103061 · Cited by 3
Sketching as a Modality in Intelligent Tutoring Systems
Long, R. A., Forbus, K., Hinrichs, T., & Hill, S. L. (2018) · Communications in computer and information science · doi:10.1007/978-3-319-92285-0_10 · Cited by 3
Self-citationSpatial adaptation: modeling a key spatial ability
Lovett, A., & Schultheis, H. (2020) · Spatial Cognition and Computation · doi:10.1080/13875868.2020.1830994 · Cited by 6
“Previous models on this platform have captured visual comparison (Sagi et al., 2012) and large-scale visual problem-solving in humans (Lovett & Forbus, 2012, 2017; Lovett et al., 2009).”
MethodSelf-citationDedre Gentner, C., & Forbus, K. D. (2025) · Current Directions in Psychological Science · doi:10.1177/09637214251395678 · Cited by 2
“The RPM task is viewed as the best predictor of human fluid intelligence, and the CogSketch model scores in the 61st percentile 6 (Lovett & Forbus, 2017)—evidence that SME performs in a humanlike way on a key test of human intelligence.”
Self-citationEye-Track Modeling of Problem-Solving in Virtual Manufacturing Environments
Zhu, R., Aqlan, F., Zhao, R., & Yang, H. Y. (2024) · ASEE Annual Conference & Exposition · doi:10.18260/1-2--37169 · Cited by 2
“For example, a study was conducted to model visual problem-solving as analogical reasoning [15].”
BackgroundGraded human sensitivity to geometric and topological concepts
Marupudi, V., & Varma, S. (2022) · Cognition · doi:10.1016/j.cognition.2022.105331 · Cited by 6
Analogical Reasoning in Mathematical Theorems
Hardiani, N., & Kristayulita, K. (2023) · JTAM (Jurnal Teori dan Aplikasi Matematika) · doi:10.31764/jtam.v7i1.10783 · Cited by 3
“This means that we compare the two domains and identify similarities in their structure so that useful conclusions can be drawn and can develop new abstractions (Lovett & Forbus, 2017).”
BackgroundGlobal relations versus object relations in visual analogies
Hashemi, A., & Tubau, E. (2024) · Thinking & Reasoning · doi:10.1080/13546783.2024.2387377 · Cited by 2
“Our results confirmed that visual reasoning could be performed at different hierarchical levels (Forbus & Lovett, 2021; Lovett & Forbus, 2017), highlighting the importance of the global path.”
Confusion Over Models: Exploring Discourse in a STEM Professional Development
Reynolds, T., Borowczak, A. C. B., & Borowczak, M. (2022) · SAGE Open · doi:10.1177/21582440221097916 · Cited by 2
“…is a combination of problem-solving and optimization for domain specific applications, while balancing the societal and ethical implications of implementing algorithms as software often executed on real-world hardware platforms (Borowczak & Burrows, 2019; Lovett & Forbus, 2017; Psycharis, 2018).”
BackgroundHummel, J. E., & Doumas, L. A. A. (2023) · Cambridge University Press eBooks · doi:10.1017/9781108755610.018 · Cited by 4
Two Computational Approaches to Visual Analogy: Task‐Specific Models Versus Domain‐General Mapping
Ichien, N., Liu, Q., Fu, S., Holyoak, K. J., Yuille, A., & Lu, H. (2023) · Cognitive Science · doi:10.1111/cogs.13347 · Cited by 5
Abstract Spatial-Temporal Reasoning via Probabilistic Abduction and Execution
Zhang, C., Jia, B., Zhu, S. C., & Zhu, Y. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2103.14230 · Cited by 2
“Psychologists have proposed reasoning systems based on symbolic representations and discrete logics [3, 37, 38, 39].”
BackgroundLearning diversified representations for visual abstract reasoning
Zhao, K., Zhu, Y. H., & Si, B. (2025) · Artificial Intelligence Review · doi:10.1007/s10462-025-11372-x · Cited by 1
“Since its introduction, this important test has been extensively studied in psychology (Carpenter et al. 1990 ; Lovett and Forbus 2017 ).”
The effect of spatial structures on analogical problem solving
Hashemi, A., & Tubau, E. (2025) · Memory & Cognition · doi:10.3758/s13421-025-01817-7 · Cited by 1
“Recent studies have demonstrated that the global spatial structure of images, beyond the characteristics of individual objects, significantly influences visual analogical reasoning (Hashemi & Tubau, 2025; Lovett & Forbus, 2017; Matlen et al., 2020).”
Tijus, C. (2020) · Studies in fuzziness and soft computing · doi:10.1007/978-3-030-54341-9_6 · Cited by 1
Computational Modeling of Basic Cognitive Functionalities
(2023) · Cambridge University Press eBooks · doi:10.1017/9781108755610.014 · Cited by 1
Relational encoding promotes creative insight for problem-solving
Kurtz, K. J., Haley, L., Longo, A., Astra, S., Meltzer, H., Suwara, G., & Patterson, J. D. (2025) · Memory & Cognition · doi:10.3758/s13421-025-01685-1 · Cited by 1
Multiple representations in cognitive architectures
Peebles, D., & Cheng, P. (2017) · Huddersfield Research Portal (University of Huddersfield) · Cited by 1
Hua, T., & Kunda, M. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1911.07736 · Cited by 3
“Knowledge-based models tend to focus on what an agent does with its knowledge during reasoning (Rasmussen and Eliasmith 2011; Kunda, McGreggor, and Goel 2013; Stranneg˚ard, Cirillo, and Str¨om 2013; Lovett and Forbus 2017); where this knowledge might come from remains an open question.”
Learning Algebraic Representation for Systematic Generalization in Abstract ReasoningPreprint
Zhang, C., Xie, S., Jia, B., Wu, Y. N., Zhu, S. C., & Zhu, Y. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2111.12990 · Cited by 1
“Early RPM-solving systems employ symbolic representation based on hand-designed features and assume access to the underlying logics [4,31,32,33].”
BackgroundRapid Unsupervised Encoding of Object Files for Visual Reasoning.
Heaton, R. F., & Hummel, J. E. (2019) · eScholarship (California Digital Library)
Mujiasih, Waluya, S. B., Kartono, K., & Mariani, S. (2020) · International Conference on Science and Education and Technology (ISET) · doi:10.2991/assehr.k.200620.024
“Problem-solving and theorem proofing in Geometry topic involve certain skills of geometric analogy reasoning (GAR) (Lovett & Forbus, 2017).”
BackgroundCorrective Processes in Modeling Reference Resolution.
Nakos, C., Rabkina, I., Hill, S. L., & Forbus, K. D. (2020) · eScholarship (California Digital Library)
Self-citationBehaviour and biases of retail investors: Task or trait?Preprint
Antoniou, C., Firth, C., Leake, D., & Stewart, N. (2021) · SSRN Electronic Journal · doi:10.2139/ssrn.3791634
DAReN: A Collaborative Approach Towards Reasoning And DisentanglingPreprint
Sahu, P., Basioti, K., & Pavlović, V. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2109.13156
Knowledge or Personality: An Empirical Analysis of Behavioural Finance and Investor Cognitive Biases
Gupta, C. (2022) · International Journal of Cyber Behavior Psychology and Learning · doi:10.4018/ijcbpl.306184
DAReN: A Collaborative Approach Towards Visual Reasoning And Disentangling
Sahu, P., Basioti, K., & Pavlović, V. (2022) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr56361.2022.9956123
Solving Diagrammatic Reasoning Problems Using Deep Learning
Choudhary, H., Dogra, D. P., & Sekh, A. A. (2023) · Communications in computer and information science · doi:10.1007/978-3-031-31417-9_29
Explicit Relational Reasoning Skills: An Index for Fostering Thinking in Biology Textbooks
", Agmon, V. A., Cuza", A. I., & Popa, N. L. (2023) · Educatia 21 · doi:10.24193/ed21.2023.24.01 · Cited by 1
Reversal Error in Mathematics: Training Against It Using ε coach
Santamarta, V., Garcia-Segarra, P., Ventura‐Campos, N., Moreno-Rus, A., & Falomir, Z. (2023) · Frontiers in artificial intelligence and applications · doi:10.3233/faia230688
Decomposing Analogy: A Logic Characterization
Leemhuis, M., Wolter, D., & Özçep, Ö. L. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-56940-1_14
Metadata
- Authors
- Lovett, A., & Forbus, K.
- Affiliations
- Northwestern University (US)
- Venue
- Psychological Review
- Published
- 2017
- Volume
- 124
- Issue
- 1
- Pages
- 60-90
- ISSN
- 0033-295X (ISSN-L)
- 1939-1471
- OpenAlex
- W2566388524
- Cited by
- 117
- References
- 94
- Citations by year
- 2026: 4 · 2025: 8 · 2024: 15 · 2023: 19 · 2022: 12 · 2021: 14 · 2020: 19 · 2019: 12 · 2018: 7 · 2017: 7
- FWCI
- 7.12
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- Psychological Review (publishedVersion)
- PubMed (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › AI-based Problem Solving and Planning
- Physical Sciences › Computer Science › Artificial Intelligence › Logic, Reasoning, and Knowledge
- Social Sciences › Psychology › Experimental and Cognitive Psychology › Categorization, perception, and language
- Keywords
- visual problem solving, analogical reasoning, Raven's Progressive Matrices, structure mapping, image comparison, abstraction, relational structures
- MeSH terms
- Adolescent, Female, Humans, Logic, Male, Models, Psychological, Problem Solving, Thinking, Visual Perception, Young Adult
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.