From Role to Person: Trust Calibration Challenges in Twin Agents

TL;DR

This paper explores trust calibration challenges in digital twin agents that represent individuals, highlighting unique issues when humans doubt their outputs and proposing new research directions.

Contribution

It introduces the concept of trust calibration challenges specific to twin agents, distinguishing them from existing frameworks and outlining key research questions.

Findings

Identifies three failure modes in trust calibration: schema gap, epistemic gap, and model artifact.

Highlights that existing trust frameworks are ineffective when the boundary between AI and human dissolves.

Proposes new research questions for developing trust calibration methods for twin agents.

Abstract

Agentic AI has taken on the role of assistant, collaborator, and decision-support tool. We argue the next role on that list is more personal: you. These are digital twins of each individual -- twin agents -- representing their knowledge, perspective, and communicative style to colleagues when they are unavailable. Drawing on early design work in an ongoing project in which agents represent knowledge workers in a professional setting, we identify a trust calibration problem specific to this approach. When a human colleague doubts a twin agent's output, they face three failure modes (a schema gap, an epistemic gap, and a model artifact) with no reliable attribution path between them. Cognitive forcing functions and related frameworks address overreliance effectively in contexts where there is a clear boundary between the AI and the human decision-maker. However, twin agents dissolve that boundary, raising a class of trust calibration challenge these frameworks were not designed to handle. We introduce the concept, distinguish it from digital twins, and outline the research questions this new class of agent demands.