cs.HCNov 3, 2026

Agentic Path Maps: Exposing an Agent's Traversal Through the Garden of Forking Paths

Authors: Madeleine Grunde-McLaughlin, Hafsah Usman, Daniel Mitroshkov, Emily Reif, Nino Migineishvili, Lakshya Chauhan. Kevin Yu, Jeffrey Heer, Daniel S. Weld

Organizations: University of Washington Seattle, Washington, USA · Allen Institute for AI Seattle, Washington, USA

Abstract

When an AI agent executes an underspecified task, it embeds choices that may contradict unarticulated user context and preferences. However, interrupting the user for clarification on all such decisions is untenable. How might agents communicate impactful, but unexplored, paths to the user after execution? To investigate, we first distill a design space for communicating alternative paths, supporting the generation of new systems and structuring dimensions of future study. We then measure the impact of one vital design space dimension on user comprehension: the number of alternatives displayed. Through a user study (n=48) in the data analysis domain, we find that participants rarely consider alternative paths of their own volition, but AI overreliance reduces when alternative paths are visualized for them. By revealing paths the agent did not take, we demonstrate how users can better interpret results and incorporate personal context.

Figures & tables

Explore similar work

CardsList
  1. Less Interaction But More Explanation: A Communication Perspective on Agentic AI Interfaces

    May 2, 2026Eunchae Jang, S. Shyam SundarExplainable Artificial IntelligenceHuman-AI Interaction

  2. Overseeing Agents Without Constant Oversight: Challenges and Opportunities

    Feb 18, 2026Madeleine Grunde-McLaughlin, Hussein Mozannar, Maya Murad +3Human Oversight of AIAgentic AI

  3. Exploring Plan Space through Conversation: An Agentic Framework for LLM-Mediated Explanations in Planning

    Mar 2, 2026Guilhem Fouilhé, Rebecca Eifler, Antonin Poché +2Multi-Agent LLM SystemsExplainable Artificial Intelligence