Towards a Distributed Platform for Normative Reasoning and Value Alignment in Multi-Agent Systems
Miguel Garcia-Bohigues, Carmengelys Cordova, Joaquin Taverner, Javier Palanca, Elena del Val, Estefania Argente
TL;DR
This work addresses enabling normative reasoning and value alignment in distributed multi-agent systems by extending the SPADE platform with deontic-norm capabilities. It introduces a normative backpack and a Normative Reasoning Engine to evaluate actions before execution, using a formal norm specification tuple to encode prohibitions and permissions within organizations. The approach aims to improve social intelligence, safety, and ethical alignment of autonomous agents, while demonstrating the workflow with a taxi-station scenario. Limitations include the current separation of norm types (prohibition vs. permission) and the ongoing need to integrate broader value reasoning and support for various agent architectures. The proposed framework lays groundwork for more trustworthy, value-driven MAS in distributed settings.
Abstract
This paper presents an extended version of the SPADE platform, which aims to empower intelligent agent systems with normative reasoning and value alignment capabilities. Normative reasoning involves evaluating social norms and their impact on decision-making, while value alignment ensures agents' actions are in line with desired principles and ethical guidelines. The extended platform equips agents with normative awareness and reasoning capabilities based on deontic logic, allowing them to assess the appropriateness of their actions and make informed decisions. By integrating normative reasoning and value alignment, the platform enhances agents' social intelligence and promotes responsible and ethical behaviors in complex environments.