Janus: a Playground for User-Involved Agentic Permission Management
Quick Answer
Janus is a novel system for user-involved agentic permission management, featuring Janus-Core for diverse designs and Janus-Harness for automated evaluation.
Quick Take
Janus is a novel system for user-involved agentic permission management, featuring Janus-Core for diverse designs and Janus-Harness for automated evaluation. It highlights the importance of user input in enhancing privacy and security while addressing cognitive load and permission fatigue, advocating for a context-sensitive approach in deploying permission assistants.
Key Points
- Janus features two components: Janus-Core for permission management designs and Janus-Harness for evaluation.
- User input significantly enhances privacy and security in agentic systems.
- AI can reduce cognitive load by augmenting user decision-making.
- Realistic user behaviors, like permission fatigue, must be considered in system design.
- No single design excels in all contexts, necessitating a tailored approach.
Paper Resources
Article Content
From source RSS / original summaryarXiv:2607. 01510v1 Announce Type: new 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.
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.AI
See more →Procedural Memory Distillation: Online Reflection for Self-Improving Language Models
Procedural Memory Distillation (PMD) enhances reinforcement learning by converting cross-episode signals into reusable memory, improving Qwen3-8B and OLMo3-Instruct-7B models by 3.8-5.5% on SCIKNOWEVAL and 7.9-13.6% on . The co-evolution of policy and memory allows for more effective self-supervision, demonstrating significant performance gains when both components are active.