Position: Digital Agents Require Unified Agent-Native Environments

摘要

Large language models (LLMs) are increasingly deployed as digital agents that perform multi-step digital work on a computer, but the environments in which they operate remain fragmented and task-specific. Our position is that digital agents need Agent-Native Computer: interfaces that expose system capabilities through compositional observation and action spaces aligned with LLM strengths. To ground this position, we showcase AgentVM, an environment running on top of a modern operating system, which integrates Graphical User Interface (GUI)-based and text-based interactions over a shared system state, and factors interaction into modular environment views. Through quantitative and qualitative analysis, we show that a unified agent-native computer is essential for building general-purpose digital agents.