Impact of Agent Reliability and Predictability on Trust in Real Time Human-Agent Collaboration

Abstract

Trust is a prerequisite for effective human-agent collaboration. While past work has studied how trust relates to an agent's reliability, it has been mainly carried out in turn based scenarios, rather than during real-time ones. Previous research identified the performance of an agent as a key factor influencing trust. In this work, we posit that an agent's predictability also plays an important role in the trust relationship, which may be observed based on users' interactions. We designed a 2x2 within-groups experiment with two baseline conditions: (1) no agent (users' individual performance), and (2) near-flawless agent (upper bound). Participants took part in an interactive aiming task where they had to collaborate with different agents that varied in terms of their predictability, and were controlled in terms of their performance. Our results show that agents whose behaviours are easier to predict have a more positive impact on task performance, reliance and trust while reducing cognitive workload. In addition, we modelled the human-agent trust relationship and demonstrated that it is possible to reliably predict users' trust ratings using real-time interaction data. This work seeks to pave the way for the development of trust-aware agents capable of adapting and responding more appropriately to users. CCS CONCEPTS • Human-centered computing → Empirical studies in HCI; Collaborative interaction; User studies; Laboratory experiments.

Trust in Artificial Intelligent Agent while Completing a Procedural Construction Task

“…The high trust, performance, and low workload for high reliable agents align with the previous literature for command and control tasks, and this result shows that while designing recommender systems for completing procedural tasks, it is essential to make sure that the reliability of the agent is higher for its users to rely on the agent (Chavaillaz et al, 2016; Daronnat et al, 2020). The presence of interaction between reliability and complexity on performance shows that the effect of low reliable AI agents deteriorates the user's performance for a complex task more than for a simple task.…”

Impact of Agents’ Errors on Performance, Reliance and Trust in Human-Agent Collaboration

“…The framework used in this study consist in a human-agent collaborative game-like scenario where participants are aided by agents. The agents assist in the process of aiming at and destroying series of incoming missiles (Daronnat et al, 2019). In this scenario, participants can either let the agents handle the aiming completely or choose to correct them by overriding the agents' inputs.…”

Conversational Information Seeking

“…First, trust between the user and a CIS system. For example, Daronnat et al (2020) studied how trust affects users satisfaction. Trust usually requires factuality.…”