Using Feasible Action-Space Reduction by Groups to fill Causal Responsibility Gaps in Spatial Interactions

2026-02-25

AI Summary

This work addresses the limitations of existing causal responsibility measures, which are confined to individual agents and fail to fairly allocate responsibility among groups in cases of causal overdetermination. To overcome this, the paper introduces the first group-oriented framework for measuring causal responsibility. By formally modeling “assertive influence,” integrating actionable state-space reduction, and employing a hierarchical identification algorithm, the approach effectively pinpoints groups that critically shape the trajectories of affected agents. Simulation experiments demonstrate the framework’s efficacy in complex multi-agent interaction scenarios and uncover systematic patterns in how interaction dynamics and agent proximity modulate group-level responsibility effects. This advances beyond the traditional individual-centric paradigm, offering a more nuanced understanding of collective causal accountability in interactive systems.

Technology Category

• Reasoning under Uncertainty: Causality
• Knowledge Representation and Reasoning: Action, Change, and Causality
• Multiagent Systems: Adversarial Agents

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems

Abstract

Heralding the advent of autonomous vehicles and mobile robots that interact with humans, responsibility in spatial interaction is burgeoning as a research topic. Even though metrics of responsibility tailored to spatial interactions have been proposed, they are mostly focused on the responsibility of individual agents. Metrics of causal responsibility focusing on individuals fail in cases of causal overdeterminism -- when many actors simultaneously cause an outcome. To fill the gaps in causal responsibility left by individual-focused metrics, we formulate a metric for the causal responsibility of groups. To identify assertive agents that are causally responsible for the trajectory of an affected agent, we further formalise the types of assertive influences and propose a tiering algorithm for systematically identifying assertive agents. Finally, we use scenario-based simulations to illustrate the benefits of considering groups and how the emergence of group effects vary with interaction dynamics and the proximity of agents.

Problem

• causal responsibility
• spatial interactions
• group responsibility
• causal overdeterminism
• autonomous agents

Innovation

• causal responsibility
• group responsibility
• spatial interaction
• action-space reduction
• autonomous agents