The DOI matches its Crossref record; 60 of the 63 references it cites were found in a registry or an index.
Believable and Effective AI Agents in Virtual Worlds: Current State and Future Perspectives
Abstract
The rapid development of complex virtual worlds (most notably, in 3D computer and video games) introduces new challenges for the creation of virtual agents, controlled by artificial intelligence (AI) systems. Two important subproblems in this topic area which need to be addressed are (a) believability and (b) effectiveness of agents’ behavior, i.e., human-likeness of the characters and high ability to achieving their own goals. In this paper, the authors study current approaches to believability and effectiveness of AI behavior in virtual worlds. They examine the concepts of believability and effectiveness, and analyze several successful attempts to address these challenges.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Citations
Cites
Flow: the psychology of optimal experience
(1990) · Choice Reviews Online · doi:10.5860/choice.28-0597 · Cited by 12,637
I.—COMPUTING MACHINERY AND INTELLIGENCE
TURING, A. M. (1950) · Mind · doi:10.1093/mind/lix.236.433 · Cited by 10,290 · cited 1×
“One of the possible approaches to the problem is to adapt a well-known Turing test (Turing, 1950) to intelligent agents, behaving in a virtual world.”
BackgroundFlow: The Psychology of Optimal Experience
Buchanan, R., & Csikszentmihalyi, M. (1991) · Design Issues · doi:10.2307/1511458 · Cited by 9,394
Reinforcement Learning: A Survey
Kaelbling, L. P., Littman, M. L., & Moore, A. W. (1996) · Journal of Artificial Intelligence Research · doi:10.1613/jair.301 · Cited by 8,972
Computing Machinery and Intelligence (1950)
Turing, A. (2004) · The Essential Turing · doi:10.1093/oso/9780198250791.003.0017 · Cited by 6,118
Sweetser (2005) · doi:10.1145/1077246.1077253 · Cited by 2,124 · cited 1×
“These observations were applied to the domain of game worlds by Sweetser and Wyeth (2005), who list the following factors, affecting user enjoyment: 1.”
MethodCooperative Multi-Agent Learning: The State of the Art
Panait, L., & Luke, S. (2005) · Autonomous Agents and Multi-Agent Systems · doi:10.1007/s10458-005-2631-2 · Cited by 1,237
Serious games : mechanisms and effects
Ritterfeld, U., Cody, M. J., & Vorderer, P. (2009) · MADOC (University of Mannheim) · Cited by 841
Toward a Definition of “Virtual Worlds”
Bell, M. W. (1970) · Journal For Virtual Worlds Research · doi:10.4101/jvwr.v1i1.283 · Cited by 456
Woolley, B. (1992) · Cited by 363
Research works printed but not linked: 14
- S.Bonacina, 2008, Evolving dodging behavior for OpenArena using neuroevolution of augmenting topologies., Urbana (Caracas, Venezuela), IL
- R.Bonse, 2004, Learning agents in Quake III (Tech. Rep.)
- Booth, M. (2004). The official counter-strike bot. In Proceedings of the Game Developers Conference.
- Chernova, S., & Veloso, M. (2007). Multiagent collaborative task learning through imitation. In Proceedings of the 4th International Symposium on Imitation in Animals and Artifacts (pp. 74-79).
- Choi, D., Konik, T., Nejati, N., Park, C., & Langley, P. (2007). A believable agent for first-person perspective games. In Proceedings of the 3rd Artificial Intelligence and Interactive Digital Entertainment International Conference.
- Hirono, D., & Thawonmas, R. (2009). Implementation of a human-like bot in a first person shooter: Second place bot at BotPrize 2008. In Proceedings of the Asia Simulation Conference.
- Isla, D. (2005). Handling complexity in the Halo 2 AI. In Proceedings of the Game Developers Conference.
- P.Langley, 2005, Interleaving learning, problem-solving, and execution in the ICARUS architecture (Tech. Rep.)
- T.Malone, 1981, What makes computer games fun?, Byte, 6, 258
- Mehta, M., Ontañón, S., & Ram, A. (2010). Meta-level behavior adaptation in real-time strategy games. In Proceedings of the Workshop on Case Based Reasoning for Computer Games.
- Orkin, J. (2006). Three states and a plan: the AI of FEAR. In Proceedings of the Game Developers Conference.
- Robertson, J., & Good, J. (2005). Adventure author: An authoring tool for 3D virtual reality story construction. In Proceedings of the Workshop on Narrative Learning Environments (pp. 63-69).
- Ros, R., Veloso, M., de Mántaras, R., Sierra, C., & Arcos, J. (2007). Beyond individualism: Modeling team playing behavior. In Proceedings of the National Conference on Artificial Intelligence (Vol. 2, pp. 1671-1674).
- S.Wintermute, 2007, SORTS (Tech. Rep.)
Cited by
Generative Agents: Interactive Simulacra of Human Behavior
Park, J. S., O'Brien, J. C., Cai, C. J., Morris, M. R., Liang, P., & Bernstein, M. S. (2023) · arXiv · doi:10.48550/arxiv.2304.03442 · Cited by 2,173
Generative Agents: Interactive Simulacra of Human Behavior
Park, J. S., O'Brien, J., Cai, C. J., Morris, M. R., Liang, P., & Bernstein, M. S. (2023) · Proceedings of the 36th Annual ACM Symposium on User Interface Software and Technology · doi:10.1145/3586183.3606763 · Cited by 2,187
Agent Supported Serious Game Environment
Terzidou, T., Tsiatsos, Τ., Miliou, C., & Sourvinou, A. (2016) · IEEE Transactions on Learning Technologies · doi:10.1109/tlt.2016.2521649 · Cited by 43
“[17],”
Applying Behavior characteristics to decision-making process to create believable game AI
Simonov, A., Сергеевич, З. А., & Fedorov, V. (2019) · Procedia Computer Science · doi:10.1016/j.procs.2019.08.222 · Cited by 22
Miyashita, S., Lian, X., Zeng, X., Matsubara, T., & Uehara, K. (2017) · ACIS International Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing (SNPD) · doi:10.1109/snpd.2017.8022767 · Cited by 16
“AI agent from the perspective of the satisfaction of the players rather than of high level of skill [5] Currently, in most commercial games, game AI is made by rule-based hard coding and takes an action according to conditional branching prepared in advance [6] However, it takes much workload to make game AI for vario…”
BackgroundImitative learning for real-time strategy games
Gemine, Q., Safadi, F., Raphael Fonteneau, D., & Ernst, D. (2012) · IEEE Conference on Computational Intelligence and Games (CIG) · doi:10.1109/cig.2012.6374186 · Cited by 15
“Some work aims at creating agents with properties that make them more fun to play with such as human-like behavior [1, 2].”
BackgroundToward Believable Acting for Autonomous Animated Characters
Curtis, C., Ađalgeirsson, S. Ö., Ciurdar, H. S., McDermott, P., Velasquez, J., Knox, W. B., Martínez, A., Gaztelumendi, D., Goussies, N. A., Liu, T., et al. (2022) · ACM SIGGRAPH Conference on Motion, Interaction and Games (MIG) · doi:10.1145/3561975.3562941 · Cited by 19
“In game research, it most often refers to gameplay: the player’s sense of immersion in a game experience [Warpefelt 2016], or a player’s perception of the human-likeness of NPCs [Umarov and Mozgovoy 2012].”
BackgroundPlatformer level design for player believability
Camilleri, E., Yannakakis, G. N., & Dingli, A. (2016) · IEEE Conference on Computational Intelligence and Games (CIG) · doi:10.1109/cig.2016.7860404 · Cited by 16
“However, a more common approach to measuring believability is through subjective assessment [1], [5], [13]–[17] where, similarly to the traditional Turing Test [18], human subjects are asked to observe a character in a game and indicate whether they believe it is being controlled by a human or by a…”
BackgroundDouglas, S., Hood, C., Overmans, T., & Scheepers, F. E. (2019) · Public Management Review · doi:10.1080/14719037.2019.1571277 · Cited by 14
“Equipping the virtual/artificial intelligence (AI) players with sufficient strategic capacity to respond intelligently to the players ’ action is very challenging (Umarov and Mozgovoy 2012).”
BackgroundInfluentialPu, K., Zhang, T., Sendhilnathan, N., Freitag, S., Sodhi, R., & Jonker, T. R. (2025) · ACM Symposium on User Interface Software and Technology (UIST) · doi:10.1145/3746059.3747770 · Cited by 37
“Another major application for memory modeling is to simulate and predict user goals or attention via memory modeling [9–11, 32, 51, 67], but few systems have attempted to model the working memory explicitly for timing decisions.”
Comp-HuSim: Persistent Digital Personality Simulation Platform
Fan, C., Tariq, Z., Bhuiyan, N. S., Yankoski, M. G., & Ford, T. W. (2024) · ACM Conference on User Modeling, Adaptation and Personalization (UMAP) · doi:10.1145/3631700.3664883 · Cited by 14
Understanding players' map exploration styles
Chen, S., Pisan, Y., & Tan, C. T. (2016) · Australasian Computer Science Week Multiconference (ACSW) · doi:10.1145/2843043.2843480 · Cited by 11
Ebrahimi, A. N. (2023) · ACM International Conference on Interactive Surfaces and Spaces (ISS) · doi:10.1145/3626485.3626551 · Cited by 7
“As artificial intelligence continues to advance, a novel form of interaction has emerged within DVWLEs, interaction with AI agents through AI-controlled avatars [30].”
BackgroundChen, X., Ong, Y.-S., Feng, L., Lim, M. H., Chen, C., & Ho, C. S. (2013) · Procedia Computer Science · doi:10.1016/j.procs.2013.10.037 · Cited by 7
Soler-Adillón, J. (2022) · Digital Creativity · doi:10.1080/14626268.2022.2154808 · Cited by 4
“The research on this regarding virtual environments is extensive (see e.g. (Bates 1994; Hayes-Roth and Doyle 1998; Mateas and Stern 2002; Hayes-Roth 2004; Umarov, Mozgovoy, and Rogers 2012; Llargues Asensio et al. 2014)).”
BackgroundNavigating the design of simulated exercising peers: insights from a participatory design study
Silacci, A., Cherubini, M., & Caon, M. (2025) · Frontiers in Digital Health · doi:10.3389/fdgth.2025.1551966 · Cited by 5
Bot Believability Assessment: A Novel Protocol & Analysis of Judge Expertise
Even, C., Bosser, A.-G., & Buche, C. (2018) · International Conference on Cyberworlds (CW) · doi:10.1109/cw.2018.00027 · Cited by 4
“However, the evaluation of such systems is complex and different approaches have been used in the past [5] giving results that can not be compared [6].”
BackgroundToward Human-like Billiard AI Bot Based on Backward Induction and Machine Learning
Tung, K. G., Wang, S. W., Tai, W. K., Way, D. L., & Chang, C. C. (2019) · IEEE Symposium Series on Computational Intelligence (SSCI) · doi:10.1109/ssci44817.2019.9003085 · Cited by 4
“As referred to the study [19], the believability or human likeness of an agent controlled by AI is determined by human users of a game.”
BackgroundUnderstanding AI Agents—A Data-Driven Literature Review
Stübinger, J., & Metz, F. (2026) · Mathematics · doi:10.3390/math14091478 · Cited by 7
Butt, N. A., Awais, M. M., Shahzadi, S., Kim, T.-H., & Ashraf, I. (2024) · Journal of King Saud University - Computer and Information Sciences · doi:10.1016/j.jksuci.2024.102182 · Cited by 3
“To achieve these goals, an AI agent should be associated with the principle of believability, Cruz (2018), Umarov and Mozgovoy (2012) and Headleand et al. (2020) which is characterized by human-like peculiarities, such as its ability to learn, make decisions, mistakes, and adjust its strategies by…”
Towards Truly Autonomous Synthetic Characters with the Sigma Cognitive Architecture
Ustun, V., & Rosenbloom, P. S. (2016) · Advances in computational intelligence and robotics book series · doi:10.4018/978-1-5225-0454-2.ch008 · Cited by 4
The Senses Beyond: New Directions in Game Engine Experiences
Weinel, J. (2024) · Springer series on cultural computing · doi:10.1007/978-3-031-53865-0_21 · Cited by 1
Song, S., Kwon, W., Oh, J., Kim, H., & Lee, J. H. (2026) · International Journal of Precision Engineering and Manufacturing · doi:10.1007/s12541-026-01611-8 · Cited by 1
“In this context, the adoption of autonomous mobile robots (AMRs) has become essential for improving internal also exhibit human-like behaviors that mirror actual human interactions, thereby enhancing engagement and providing a more sophisticated user experience [ 5, 6].”
An Approach To Artificial Society Generation For Video Games
Sarlo, B. B. (2015) · Scholarship@Western (Western University) · Cited by 1
Examining Emotional Responses to Effective Versus Ineffective Virtual Buddies
Ingraham, K. M. (2014) · Journal of International Crisis and Risk Communication Research · Cited by 1
A Graphical Tool for the Creation of Behaviors in Virtual Worlds
Corradini, A., & Mehta, M. (2019) · Natural Language Processing · doi:10.4018/978-1-7998-0951-7.ch028 · Cited by 1
Towards Human-Like Virtual Beings: Simulating Human Behavior in 3D Scenes
Liang, C., Wang, W., & Yang, Y. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01001 · Cited by 6
“They provide a brute force way of manually crafting agent’s behaviors, but cannot perform new procedures that were not hard-coded in their script [22], limiting the generalizability.”
Morgan, E., & Papangelis, K. (2015) · Communications in computer and information science · doi:10.1007/978-3-319-21380-4_128 · Cited by 1
Chen, X., Ong, Y.-S., Feng, L., Lim, M. H., Chen, C., & Ho, C. S. (2013)
Artificial society generation for modern video games
Sarlo, B. B., & Katchabaw, M. J. (2015) · IEEE Games, Entertainment, Media Conference (GEM) · doi:10.1109/gem.2015.7377236
“This has led to believable agents with a large set of independent traits that then influence their actions and behaviours [5], as well as believable behaviour systems for creating autonomous agents [6,7].”
BackgroundA Graphical Tool for the Creation of Behaviors in Virtual Worlds
Corradini, A., & Mehta, M. (2016) · Advances in computational intelligence and robotics book series · doi:10.4018/978-1-5225-0454-2.ch003
Implementation of Collision Avoidance System Algorithm in NPC Game 3D
Hamanako, G. A., & Sucipto, A. (2023) · Journal of Information Technology and Its Utilization · doi:10.56873/jitu.6.1.4988
“NPCs can be intelligent agents created by embedding Artificial Intelligence (AI) having human-like behavior, such as changing their strategy or mindset in response to the opponent's actions [3].”
BackgroundResearch of Crowd Behavior Simulation Methods Based on Relationships and Emotional Evolution
Gu, Z., Gao, T., Bai, Z., & Mi, Q. (2026) · ACM Transactions on Modeling and Computer Simulation · doi:10.1145/3787458 · Cited by 2
“The “believability” of a virtual agent is not merely about executing tasks efficiently but about 6:2 Z. Gu et al. exhibiting nuanced, internally-motivated behaviors that mirror the complexity of human conduct [ 15 ].”
Metadata
- Authors
- Umarov, I., & Mozgovoy, M.
- Affiliations
- TruSoft International Inc., USA
- University of Aizu (JP)
- ORCID
- Mozgovoy, Maxim
- Venue
- International Journal of Gaming and Computer-Mediated Simulations
- Publisher
- IGI Global Scientific Publishing
- Published
- 2012-04-01
- Volume
- 4
- Issue
- 2
- Pages
- 37-59
- ISSN
- 1942-3888 (ISSN-L)
- 1942-3896
- OpenAlex
- W2098535914
- Semantic Scholar
- e923908c24fb95a266d66cfd812fbb2efbafb2ac
- Cited by
- 32
- References
- 63
- Citations by year
- 2026: 3 · 2025: 3 · 2024: 3 · 2023: 3 · 2022: 2 · 2019: 4 · 2018: 1 · 2017: 1 · 2016: 5 · 2015: 3 · 2014: 1 · 2013: 2 · 2012: 1
- FWCI
- 2.20
- Type
- journal article
- Language
- ng
- Open access
- closed
- Locations
- International Journal of Gaming and Computer-Mediated Simulations (publishedVersion)
- RePEc: Research Papers in Economics (submittedVersion)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Artificial Intelligence in Games
- Social Sciences › Psychology › Social Psychology › Social Robot Interaction and HRI
- Social Sciences › Sociology and Political Science › Digital Games and Media
- Keywords
- virtual agents, believable agents, virtual worlds, 3D computer games, video games, human-likeness, goal achievement, game AI
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.