The DOI matches its Crossref record; 49 of the 49 references it cites were found in a registry or an index.
Cooperative Resilience in Artificial Intelligence Multiagent Systems
Open accessAbstract
Resilience refers to the ability of systems to with-stand, adapt to, and recover from disruptive events. While studies on resilience have attracted significant attention across various research domains, the precise definition of this concept within the field of cooperative artificial intelligence remains unclear. This paper addresses this gap by proposing a clear definition of ‘cooperative resilience’ and outlining a methodology for its quantitative measurement. The methodology is validated in an environment with RL-based and LLM-augmented autonomous agents, subjected to environmental changes and the introduction of agents with unsustainable behaviors. These events are parameterized to create various scenarios for measuring cooperative resilience. The results highlight the crucial role of resilience metrics in analyzing how the collective system prepares for, resists, recovers from, sustains well-being, and transforms in the face of disruptions. These findings provide foundational insights into the definition, measurement, and preliminary analysis of cooperative resilience, offering significant implications for the broader field of AI. Moreover, the methodology and metrics developed here can be adapted to a wide range of AI applications, enhancing the reliability and effectiveness of AI in dynamic and unpredictable environments.
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
“Unlike conventional automation scripts, which follow deterministic workflows, AI Agents demonstrate reactive intelligence and some level of adaptability, allowing them to interpret dynamic inputs and reconfigure outputs accordingly [50].”
From AI Agents vs. Agentic AI: A Conceptual taxonomy, applications and challenges (2026) · cites this paper as [50]
Citations
Cites
Resilience and Stability of Ecological Systems
Holling, C. S. (1973) · Annual Review of Ecology and Systematics · doi:10.1146/annurev.es.04.110173.000245 · Cited by 18,995 · cited 3×
“Here, the resilient entity is an ecological system, and the disruptive event involves disruptions in population dynamics [33].”
Bibliographical review on reconfigurable fault-tolerant control systems
Zhang, Y., & Jiang, J. (2008) · Annual Reviews in Control · doi:10.1016/j.arcontrol.2008.03.008 · Cited by 2,652 · cited 1×
“In engineering, these disruptions often involve failures [44], [45], errors, or adversarial attacks [6], [7], with resilience linked to terms such as resist, recover, and adapt [10], [11], [37], [41].”
Psychological Resilience: A Review and Critique of Definitions, Concepts, and Theory
Fletcher, D., & Sarkar, M. (2013) · European Psychologist · doi:10.1027/1016-9040/a000124 · Cited by 2,547
The economic resilience of regions: towards an evolutionary approach
Simmie, J., & Martin, R. (2010) · Cambridge Journal of Regions, Economy and Society · doi:10.1093/cjres/rsp029 · Cited by 1,671 · cited 2×
“…intelligence (AI) systems [5], [6], [7], [8], [9], engineering [10], [11], [12], psychology [13], [14], [15], [16], [17], [18], economy [19], [20], [21], social science [22], [23], network science [24], [25], [26], [27], dynamical systems theory [28], [29], [30], multirobot systems [31], and…”
Herrman, H., Stewart, D. E., Diaz-Granados, N., Berger, E. L., Jackson, B., & Yuen, T. (2011) · The Canadian Journal of Psychiatry · doi:10.1177/070674371105600504 · Cited by 1,338
Universal resilience patterns in complex networks
Gao, J., Barzel, B., & Barabási, A.-L. (2016) · Nature · doi:10.1038/nature16948 · Cited by 1,217
Rose, A. (2007) · Environmental Hazards · doi:10.1016/j.envhaz.2007.10.001 · Cited by 945 · cited 2×
“In economics, resilience is linked with actions such as withstand, grow, and resist, and the disruptions are associated with terms such as risk, crisis, and change [19], [20], [21].”
Economic Vulnerability and Resilience: Concepts and Measurements
Briguglio, L., Cordina, G., Farrugia, N., & Vella, S. (2009) · Oxford Development Studies · doi:10.1080/13600810903089893 · Cited by 878 · cited 2×
“…intelligence (AI) systems [5], [6], [7], [8], [9], engineering [10], [11], [12], psychology [13], [14], [15], [16], [17], [18], economy [19], [20], [21], social science [22], [23], network science [24], [25], [26], [27], dynamical systems theory [28], [29], [30], multirobot systems [31], and…”
What is social resilience? Lessons learned and ways forward
Keck, M., & Sakdapolrak, P. (2013) · Erdkunde · doi:10.3112/erdkunde.2013.01.02 · Cited by 830 · cited 1×
“…[5], [6], [7], [8], [9], engineering [10], [11], [12], psychology [13], [14], [15], [16], [17], [18], economy [19], [20], [21], social science [22], [23], network science [24], [25], [26], [27], dynamical systems theory [28], [29], [30], multirobot systems [31], and ecology [32], [33], [34].”
Wu, G., Feder, A., Cohen, H., Kim, J. J., Calderon, S., Charney, D. S., & Mathé, A. A. (2013) · Frontiers in Behavioral Neuroscience · doi:10.3389/fnbeh.2013.00010 · Cited by 726 · cited 2×
“In psychology, a resilience entity spans from individuals to groups such as families and communities [13], [14], [15], [16], [46], [47], with disruptions related with stress, threats, and disturbances that are embedded in life events [13], [14], [15], [16].”
Research works printed but not linked: 13
- Petrilli, Measuring resilience in artificial intelligence and machine learning systems
- 10.1037/0002-9432.71.3.290 · doi:10.1037/0002-9432.71.3.290 · Paper page
- Ozbay, 2007, Social support and resilience to stress: From neurobiology to clinical practice, Psychiatry (Edgmont), 4
- Barabási, 2016, Network Science
- Dafoe, 2020, Open problems in cooperative AI, arXiv:2012.08630. · arXiv
- Agapiou, 2022, Melting Pot 2.0, arXiv:2211.13746. · arXiv
- Perolat, 2017, A multi-agent reinforcement learning model of common-pool resource appropriation, Adv. Neural Inf. Process. Syst., 30, 3643
- Schulman, 2017, Proximal policy optimization algorithms, arXiv:1707.06347. · arXiv
- Cross, 2024, Hypothetical minds: Scaffolding theory of mind for multi-agent tasks with large language models, arXiv:2407.07086. · arXiv
- Wei, 2022, Chain-of-thought prompting elicits reasoning in large language models, Adv. Neural Inf. Process. Syst., 35, 24824
- Zhou, 2024, Self-discover: Large language models self-compose reasoning structures, arXiv:2402.03620. · arXiv
- Piatti, 2025, Cooperate or collapse: Emergence of sustainable cooperation in a society of LLM agents, Adv. Neural Inf. Process. Syst., 37, 111715
- Willis, 2025, Will systems of LLM agents cooperate: An investigation into a social dilemma, arXiv:2501.16173. · arXiv
Cited by
AI Agents vs. Agentic AI: A Conceptual taxonomy, applications and challenges
Sapkota, R., Roumeliotis, K. I., & Karkee, M. (2026) · Information Fusion · doi:10.1016/j.inffus.2025.103599 · Cited by 671
“Unlike conventional automation scripts, which follow deterministic workflows, AI Agents demonstrate reactive intelligence and some level of adaptability, allowing them to interpret dynamic inputs and reconfigure outputs accordingly [50].”
AI Agents vs. Agentic AI: A Conceptual Taxonomy, Applications and Challenges
Sapkota, R., Roumeliotis, K. I., & Karkee, M. (2025) · arXiv · doi:10.48550/arxiv.2505.10468 · Cited by 295
“Unlike conventional automation scripts, which follow deterministic workflows, AI Agents demonstrate reactive intelligence and some level of adaptability, allowing them to interpret dynamic inputs and reconfigure outputs accordingly [50].”
AI Agents vs. Agentic AI: A Conceptual Taxonomy, Applications and Challenges
Sapkota, R., Roumeliotis, K. I., & Karkee, M. (2025) · SuperIntelligence - Robotics - Safety & Alignment · doi:10.70777/si.v2i3.15161 · Cited by 186
Martínez, R. S., García-Castillo, F., López-Sánchez, C., & del Castillo, J. A. G. (2025) · Behavioral Sciences · doi:10.3390/bs15111573 · Cited by 13
“Thus, AI positions itself as a tool with the potential to strengthen both the cognitive and socio-emotional competencies necessary for academic and personal success (Bartz et al., 2023; Chacon-Chamorro et al., 2024; Rehman et al., 2021).”
Khairi, S. M. M., Rozali, N., Sobry, S. C., & Nor, N. M. (2025) · Environment-Behaviour Proceedings Journal · doi:10.21834/e-bpj.v10isi28.6973 · Cited by 2
Metadata
- Authors
- Chacon-Chamorro, M., Felipe Giraldo, L., Quijano, N., Vargas-Panesso, V., González, C., Pinzón, J. S., Manrique, R., Ríos, M., Fonseca, Y., Gómez-Barrera, D., & Perdomo-Pérez, M.
- Affiliations
- Universidad de Los Andes (CO)
- School of Engineering, Universidad de los Andes, Bogotá, Colombia
- Center of Excellence in Analytics and Artificial Intelligence, Bancolombia, Bogotá, Colombia
- School of Humanities, Arts, and Social Sciences, Universidad de Ibagué, Ibagué, Colombia
- ORCID
- Venue
- IEEE Transactions on Artificial Intelligence
- Published
- 2025-12
- Volume
- 6
- Issue
- 12
- Pages
- 3430-3440
- ISSN
- 2691-4581 (ISSN-L)
- OpenAlex
- W4410114620
- Cited by
- 5
- References
- 49
- Citations by year
- 2026: 2 · 2025: 3
- FWCI
- 2.02
- Type
- journal article
- Language
- en
- Open access
- green
- arxiv.org
- Licence
- Locations
- IEEE Transactions on Artificial Intelligence (publishedVersion)
- arXiv (Cornell University) (submittedVersion, cc-by)
- arXiv (Cornell University) (cc-by)
- Funders
- Google, Inc., through the Google Research Scholar Program
- UniAndes–DeepMind Scholarship 2023.
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Multi-Agent Systems and Negotiation
- Physical Sciences › Engineering › Control and Systems Engineering › Systems Engineering Methodologies and Applications
- Physical Sciences › Computer Science › Artificial Intelligence › Adversarial Robustness in Machine Learning
- Keywords
- cooperative resilience, multi-agent systems, resilience indicators, reinforcement learning agents
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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Cooperative Resilience in Artificial Intelligence Multiagent Systems. https://app.cochat.ai/papers/10.1109/tai.2025.3567371
- The paper
- Chacon-Chamorro, M., Felipe Giraldo, L., Quijano, N., Vargas-Panesso, V., González, C., Pinzón, J. S., Manrique, R., Ríos, M., Fonseca, Y., Gómez-Barrera, D., & Perdomo-Pérez, M. (2025). Cooperative Resilience in Artificial Intelligence Multiagent Systems. IEEE Transactions on Artificial Intelligence. https://doi.org/10.1109/tai.2025.3567371
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.