Paper frames work agents as systems that deliver verifiable outcomes
Original title: Work Agents: Systems, Capabilities, and Optimization
It defines work persistence and openness, five work forms, and five capability families for reliable execution.
A survey treats work agents as foundation models plus runtime harnesses that execute tasks in stateful workspaces and produce verifiable outcomes. It introduces work persistence and work openness, and classifies digital work into five forms by task scope and organization. The paper reviews model, harness, and joint optimization, plus outcome-based evaluation methods. Future directions include sustained delegation and adaptation to open environments.
- Agents are defined as models combined with runtime harnesses.
- Five capability families are identified for reliable work execution.
- Optimization covers models, harnesses, and their joint design.
- Evaluation is analyzed from the perspective of work outcomes.
From the original article
1 min read at huggingface.co
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.
By Zishan Xu, Enjun Du, Mingqi Gao · huggingface.co
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.