Outputs (54)

Surprise! Surprise! Learn and Adapt (2024)
Presentation / Conference Contribution
Samin, H., Walton, D., & Bencomo, N. (2025, May). Surprise! Surprise! Learn and Adapt. Presented at 24th International Conference on Autonomous Agents and Multiagent Systems, Detroit, Michigan, USA

Self-adaptive systems (SAS) adjust their behavior at runtime in response to environmental changes, which are often unpredictable at design time. SAS must make decisions under uncertainty, balancing trade-offs between quality attributes (e.g., cost mi... Read More about Surprise! Surprise! Learn and Adapt.

Beyond Syntax: How Do LLMs Understand Code? (2024)
Presentation / Conference Contribution
North, M., Atapour-Abarghouei, A., & Bencomo, N. (2025, April). Beyond Syntax: How Do LLMs Understand Code?. Presented at 2025 IEEE/ACM International Conference on Software Engineering ICSE, Ottawa , Canada

Within software engineering research, Large Language Models (LLMs) are often treated as 'black boxes', with only their inputs and outputs being considered. In this paper, we take a machine interpretability approach to examine how LLMs internally repr... Read More about Beyond Syntax: How Do LLMs Understand Code?.

Declarative Lifecycle Management in Digital Twins (2024)
Presentation / Conference Contribution
Bencomo, N., Kamburjan, E., Tapia Tarifa, S. L., & Broch-Johnsen, E. (2024, September). Declarative Lifecycle Management in Digital Twins. Presented at 1st International Conference on Engineering Digital Twins (EDTconf 2024), Linz, Austria

Together, a digital twin and its physical counterpart can be seen as a self-adaptive system: the digital twin monitors the physical system, updates its own internal model of the physical system, and adjusts the physical system by means of controllers... Read More about Declarative Lifecycle Management in Digital Twins.

Code Gradients: Towards Automated Traceability of LLM-Generated Code (2024)
Presentation / Conference Contribution
North, M., Atapour-Abarghouei, A., & Bencomo, N. (2024, June). Code Gradients: Towards Automated Traceability of LLM-Generated Code. Presented at 2024 IEEE 32nd International Requirements Engineering Conference (RE), Reykjavik, Iceland

Large language models (LLMs) have recently seen huge growth in capability and usage. Within software engineering, LLMs are increasingly being used by developers to generate code. Code generated by an LLM can be seen essentially a continuous mapping f... Read More about Code Gradients: Towards Automated Traceability of LLM-Generated Code.

Uncertainty Flow Diagrams: Towards a Systematic Representation of Uncertainty Propagation and Interaction in Adaptive Systems (2024)
Presentation / Conference Contribution
Camara, J., Hahner, S., Perez-Palacin, D., Vallecillo, A., Acosta, M., Bencomo, N., Calinescu, R., & Gerasimou, S. (2024, April). Uncertainty Flow Diagrams: Towards a Systematic Representation of Uncertainty Propagation and Interaction in Adaptive Systems. Presented at 2024 IEEE/ACM 19th Symposium on Software Engineering for Adaptive and Self-Managing Systems, Lisbon, Portugal

Sources of uncertainty in adaptive systems are rarely independent, and their interaction can affect the attainment of system goals in unpredictable ways. Despite ample work on “taming” uncertainty, the research community has devoted little attention... Read More about Uncertainty Flow Diagrams: Towards a Systematic Representation of Uncertainty Propagation and Interaction in Adaptive Systems.

Latency-aware RDMSim: Enabling the Investigation of Latency in Self-Adaptation for the Case of Remote Data Mirroring (2024)
Presentation / Conference Contribution
Götz, S., Samin, H., & Bencomo, N. (2024, April). Latency-aware RDMSim: Enabling the Investigation of Latency in Self-Adaptation for the Case of Remote Data Mirroring. Presented at SEAMS '24: 19th International Conference on Software Engineering for Adaptive and Self-Managing Systems, Lisbon, Portugal

Self-adaptive systems are able to adapt themselves according to changing contextual conditions to ensure a set of predefined objectives (e.g., certain non-functional requirements like reliability) is reached. For this, they perform adaptation actions... Read More about Latency-aware RDMSim: Enabling the Investigation of Latency in Self-Adaptation for the Case of Remote Data Mirroring.

Responsible AI governance: A response to UN interim report on governing AI for humanity (2024)
Report
Bencomo, N., Kiden, S., Deshmukh, J., Williams, J., Ramchurn, G., Stein, S., Yazdanpanah, V., Stahl, B., Townsend, B., Maple, C., Vincent, C., Sampson, F., Gilbert, G., Ross, J., Martinez del Rincon, J., Lisinska, J., O’Shea, K., Da Costa Abreu, M., Deb, O., Winter, P., …Iniesta, R. (2024). Responsible AI governance: A response to UN interim report on governing AI for humanity. United Nations

A response to UN interim report on governing AI for humanity

Decision Making for Self-adaptation based on Partially Observable Satisfaction of Non-Functional Requirements (2024)
Journal Article
Garcia, L., Samin, H., & Bencomo, N. (2024). Decision Making for Self-adaptation based on Partially Observable Satisfaction of Non-Functional Requirements. ACM Transactions on Autonomous and Adaptive Systems, 19(2), 1-44. https://doi.org/10.1145/3643889

Approaches that support the decision-making of self-adaptive and autonomous systems (SAS) often consider an idealized situation where (i) the system’s state is treated as fully observable by the monitoring infrastructure, and (ii) adaptation actions... Read More about Decision Making for Self-adaptation based on Partially Observable Satisfaction of Non-Functional Requirements.

Automated Provenance Collection at Runtime as a Cross-Cutting Concern (2023)
Presentation / Conference Contribution
James Reynolds, O., García-Domínguez, A., & Bencomo, N. (2023, October). Automated Provenance Collection at Runtime as a Cross-Cutting Concern. Presented at 2023 ACM/IEEE International Conference on Model Driven Engineering Languages and Systems Companion (MODELS-C), Västerås, Sweden

Autonomous decision-making is increasingly applied to handle highly dynamic, uncertain environments: as incorrect decisions can cause serious harm to individuals or society, there is a need for accountability. For systems that use runtime models to r... Read More about Automated Provenance Collection at Runtime as a Cross-Cutting Concern.

To download or not to download the Covid-19 Track and Trace App? What is more influential in users’ minds? (2023)
Journal Article
Sutcliffe, A., Bencomo, N., Darby, A., Paucar, L. H., & Sawyer, P. (2023). To download or not to download the Covid-19 Track and Trace App? What is more influential in users’ minds?. International Journal of Human-Computer Studies, 180, Article 103140. https://doi.org/10.1016/j.ijhcs.2023.103140

Objectives
to investigate the role of values in technology acceptance in general and in the context of the UK Covid Track and Trace App.

Methods
A survey and interview study was conducted to elicit users’ perceptions of values in general, values... Read More about To download or not to download the Covid-19 Track and Trace App? What is more influential in users’ minds?.