InnerPond: Fostering Inter-Self Dialogue with a Multi-Agent Approach for Introspection

2026-03-29

AI Summary

This work addresses the limitation of existing digital tools that conceptualize the self as a unified whole, thereby failing to support introspection grounded in multiple internal perspectives. To overcome this, the authors propose InnerPond—the first system integrating Dialogical Self Theory with multi-agent large language models (LLMs)—which models an individual’s values, concerns, and aspirations as distinct LLM-based agents. These agents interact within a shared space through spatial metaphors and orchestrated dialogue mechanisms, enabling users to collaboratively create and observe their “inner voices” to construct a relational map of the self. In a study with 17 young adults navigating career decisions, InnerPond effectively facilitated exploration of plural selves and guided introspection, demonstrating the feasibility and value of this approach.

Abstract

Introspection is central to identity construction and future planning, yet most digital tools approach the self as a unified entity. In contrast, Dialogical Self Theory (DST) views the self as composed of multiple internal perspectives, such as values, concerns, and aspirations, that can come into tension or dialogue with one another. Building on this view, we designed InnerPond, a research probe in the form of a multi-agent system that represents these internal perspectives as distinct LLM-based agents for introspection. Its design was shaped through iterative explorations of spatial metaphors, interaction scaffolding, and conversational orchestration, culminating in a shared spatial environment for organizing and relating multiple inner perspectives. In a user study with 17 young adults navigating career choices, participants engaged with the probe by co-creating inner voices with AI, composing relational inner landscapes, and orchestrating dialogue as observers and mediators, offering insight into how such systems could support introspection. Overall, this work offers design implications for AI-supported introspection tools that enable exploration of the self's multiplicity.

Problem

• introspection
• Dialogical Self Theory
• multi-agent system
• self-multiplicity
• inner perspectives

Innovation

• multi-agent system
• Dialogical Self Theory
• LLM-based agents
• spatial metaphor
• AI-supported introspection