Janus: a Playground for User-Involved Agentic Permission Management

2026-07-01

AI Summary

This work addresses the underexplored role of users in permission management for AI agents that autonomously invoke tools. The authors propose Janus, a system comprising Janus-Core—a framework supporting diverse permission designs—and Janus-Harness, an automated evaluation suite. They formalize, for the first time, the design space of user-involved agent permission management and implement six permission assistants for empirical assessment. Leveraging a modular agent architecture, synthetic responder simulation, and AI-augmented decision-making, their study demonstrates that active user involvement significantly enhances security, while AI assistance effectively reduces cognitive load. Crucially, no one-size-fits-all solution exists; instead, context-sensitive mechanisms that dynamically adapt to situational demands are essential to jointly preserve privacy and maintain usability.

Abstract

AI agents that autonomously execute tool calls on a user's behalf raise pressing questions about permission management: what role could users play, and what role should they play? Despite many proposed approaches, the user's role in agentic permission management remains under explored. We introduce Janus, a playground system for implementing and evaluating user-involved agentic permission management designs. Janus consists of two components: Janus-Core, a modular agentic system supporting a diverse spectrum of permission management designs, and Janus-Harness, an automated evaluation framework. Grounded in a conceptual model that identifies key design axes for user involvement, we implement six permission assistants spanning the design space and evaluate them across three scenarios and three synthetic responders. We demonstrate that user input is critical and can significantly strengthen privacy and security, that AI augmentation of user decisions can help reduce cognitive load, and that realistic user behavior including permission fatigue must be accounted for in system design. No single design performs optimally across all contexts, motivating a more principled and context-sensitive approach to deploying permission assistants in agentic systems. Janus is publicly available to support future investigation into this dimension of agentic system design.

Problem

• agentic permission management
• user involvement
• AI agents
• privacy and security
• permission fatigue

Innovation

• agentic permission management
• user involvement
• modular agent system
• automated evaluation framework
• permission fatigue