[TMP-005] A model and architecture for multi-context, value-aware agents
A model of values preferences for AI agents to address simultaneous multiple layered contexts in which they are situated.
Short description
This project seeks to formalize how AI agents can interpret and act according to socio-ethical values within complex, layered social contexts. The goal is to integrate stakeholders' values, norms, and conventions into AI decision-making processes. This enables ethics-by-design approaches where agents align their behaviour with the broader social values relevant to their interactions. While existing literature on value systems often focuses on either abstract or specific contexts, this project addresses the challenge of multiple overlapping contexts where value preferences may conflict or shift depending on the situation.
The projects' outcomes show that:
- Adding value preferences and contexts delivers more realistic results in a water-consumption multi-agent simulation
- Given our grounding in the Schwartz’s circumflex model of values and a value preference, some value orders are more prone to shift than others, that is, they are more flexible in terms of changing their preferences
This project is a collaboration between Instituto Superior Técnico, Umea University, Universitat Politecnica Catalunya and Bath University.
Additional information
An exploratory exercise of values and preferences was carried out which would guide this formalization. This resulted in different outcomes:
1. An agent-based model (ABM) with values and value preferences as part of agents’ deliberation as well as contexts expressed as value preferences. Contexts affected agents in such a way that it may result in them temporarily changing their value preferences according to an effort function (we assumed such effort would be proportional to how much importance each agent gave to their values)
2. A software implementing the above-mentioned model. The code of the ABM can be found in this repository: https://github.com/HPAI-BSC/value-based-water-consumption/
3. A workshop paper presenting the results of experimenting with such ABM.
Oliva-Felipe, L., Lobo, I., McKinlay, J., Dignum, F., De Vos, M., Cortés, U., Cortés, A. (2024). Context Matters: Contextual Value-Based Deliberation in Water Consumption Scenarios. In: XXX, Y., et al. Artificial Intelligence. ECAI 2024 International Workshops. ECAI 2024. Communications in Computer and Information Science, vol XXXX. Springer, Cham. https://doi.org/XXXX/YYYYY (accepted, to be printed)
These outputs are intended to guide the subsequent formalization and architecture design for value-aware agents.
Technical categories
Multi-agent systems
Technology Readiness Level
TRL 1-2 (Basic research)
Lead institution
Last updated
Wed, 11/20/2024 - 13:45
Contact details
Rui Prada, rui.prada@tecnico.ulisboa.pt