Work Agents: Systems, Capabilities, and Optimization

As foundation models evolve from information generation to digital work execution, agents are increasingly capable of completing complex tasks across tools, applications, and workflows. However, existing research lacks a unified perspective on how agents reliably accomplish delegated work. This survey presents a work-centric, system-level perspective that views work agents as systems combining foundation models and runtime harnesses to execute tasks in stateful workspaces and deliver verifiable outcomes. It introduces work persistence and work openness as two complementary dimensions, organizes digital work into five forms, identifies five core capability families, and examines model, harness, and joint optimization. It also reviews evaluation methods and metrics from the perspective of work outcomes and discusses future directions for sustained work delegation, adaptation to open environments, and capability improvement.

Preprint